Kunpeng Kang, Shuaimin Li, Kaiyuan Zhang, Luyang Zhang, Jiasheng Si, Bing Xu, Kehai Chen, Muyun Yang, Wenpeng Lu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Yeqing Teng, Jiasheng Si, Shuxia Lin, Linhai Zhang, Weiyu Zhang, Wenpeng Lu, Deyu Zhou, Xiaoming Wu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Enming Wang, Jianlei Wang, Xueping Peng, Hongjiao Guan, Yinglong Wang, Sibo Wei, Jianbin Guo, Ruifeng Xu, Wenpeng Lu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zhen Yang, Ping Jian, Zhongbin Guo, Zuming Zhang, Chengzhi Li, Yonghong Deng, Xinyue Zhang, Wenpeng Lu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Depression has become a critical global public health challenge, creating an urgent need for automated and scalable screening solutions. Social media platforms, which capture rich and spontaneous multi-modal behavioral data, offer a promising avenue for detecting early signs of mental distress. However, existing depression detection methods predominantly rely on static multi-modal fusion strategies and frequently fail to effectively tackle cross-modal semantic gaps. To address these limitations, we propose a Mutual Guidance Multi-modal Network with Complementary Graph Learning (MGMN) for depression detection by observing individuals' behavioral performance on social media. Specifically, a cross-modal mutual guidance mechanism is designed to dynamically construct a complementary graph by using mutual similarities within and across visual and acoustic modalities common in social media. More specifically, based on this complementary graph, a modality-specific adaptive residual learning module is applied to each modality to stabilize deep feature learning and preserve modality-specific and complementary information via graph-conditioned adaptive residual fusion. Furthermore, the refined uni-modal features are subsequently fed into a joint-modal fusion and prediction module to output the final disease prediction probability. Extensive experiments on the MUD3, LMVD, and D-vlog datasets demonstrate our proposed method's superiority over state-of-the-art methods, confirming that the proposed framework provides a robust and effective solution for mental health monitoring. Codes are available at https://github.com/Petofi-romance/MGMN

Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social environment. However, malicious users persistently develop evasive perturbations to disguise toxic content and evade detectors. Traditional detectors or methods are static over time and are inadequate in addressing these evolving evasion tactics. Thus, continual learning emerges as a logical approach to dynamically update detection ability against evolving perturbations. Nevertheless, disparities across perturbations hinder the detector's continual learning on perturbed text. More importantly, perturbation-induced noises distort semantics to degrade comprehension and also impair critical feature learning to render detection sensitive to perturbations. These amplify the challenge of continual learning against evolving perturbations.

With the proliferation of multi-modal data, safe and efficient multi-modal hashing retrieval has become a pressing research challenge, particularly due to concerns over data privacy during centralized processing. To address this, we propose Prototype-based Federated Multi-modal Hashing (PFMH), an innovative framework that seamlessly integrates federated learning with multi-modal hashing techniques. PFMH achieves fine-grained fusion of heterogeneous multi-modal data, enhancing retrieval accuracy while ensuring data privacy through prototype-based communication, thereby reducing communication costs and mitigating risks of data leakage. Furthermore, using a prototype completion strategy, PFMH tackles class imbalance and statistical heterogeneity in multi-modal data, improving model generalization and performance across diverse data distributions. Extensive experiments demonstrate the efficiency and effectiveness of PFMH within the federated learning framework, enabling distributed training for secure and precise multi-modal retrieval in real-world scenarios.

Investigating hallucination issues in large language models (LLMs) within cross-lingual and cross-modal scenarios can greatly advance the large-scale deployment in real-world applications.Nevertheless, the current studies are limited to a single scenario, either cross-lingual or cross-modal, leaving a gap in the exploration of hallucinations in the joint cross-lingual and cross-modal scenarios.Motivated by this, we introduce a novel joint Cross-lingual and Crossmodal Hallucinations benchmark (CCHall) to fill this gap.Specifically, CCHall simultaneously incorporates both cross-lingual and cross-modal hallucination scenarios, which can be used to assess the cross-lingual and crossmodal capabilities of LLMs.Furthermore, we conduct a comprehensive evaluation on CCHall, exploring both mainstream opensource and closed-source LLMs.The experimental results highlight that current LLMs still struggle with CCHall.We hope CCHall can serve as a valuable resource to assess LLMs in joint cross-lingual and cross-modal scenarios.

The International Classification of Diseases (ICD) coding is a crucial component for standardizing medical information, and automated coding represents an important direction for improving the efficiency and accuracy of this process. However, current automated ICD coding research still faces significant challenges. First, existing studies are predominantly based on English contexts, making their models difficult to directly apply to China's localized ICD versions, while the immense pressure on its healthcare system makes this research particularly urgent in China. In addition, mainstream approaches oversimplify coding as multi-label classification, thus ignoring the coder workflow and failing to generalize to unseen codes or uncover implicit diagnoses. To address these challenges, we propose AiCoder, a novel multi-agent framework that simulates real-world coding workflows through a two-stage design. The first stage focuses on accuracy by parsing discharge diagnoses, correlating medical record evidence, and utilizing knowledge graphs for standardization; the second stage emphasizes completeness by leveraging ICD hierarchical structures and integrating clinical reasoning patterns to identify potentially missed codes. Furthermore, we construct a publicly available high-quality Chinese ICD annotation dataset, providing a valuable resource for the research community. Comprehensive experiments including ablation study and case study validate our framework's effectiveness. We also systematically analyze common coding errors of LLMs in Chinese ICD coding tasks, hoping to provide reference for future research.

Over-correction is a critical issue for large language models (LLMs) to address Grammatical Error Correction (GEC) task, esp. for Chinese. This paper proposes a Chain-of-Task (CoTask) framework to reduce over-correction. The CoTask framework is applied as multi-task instruction tuning of LLMs by decomposing the process of grammatical error analysis to design auxiliary tasks and adjusting the types and combinations of training tasks. A supervised fine-tuning (SFT) strategy is also presented to enhance the performance of LLMs, together with an algorithm for automatic dataset annotation to avoid additional manual costs. Experimental results demonstrate that our method achieves new state-of-the-art results on both FCGEC (in-domain) and NaCGEC (out-of-domain) test sets.

Accurately evaluating the word sense disambiguation (WSD) capabilities of large language models (LLMs) remains challenging, as existing studies primarily rely on single-task evaluations and classification-based metrics that overlook the fundamental differences between generative LLMs and traditional classification models.To bridge this gap, we propose RoDEval, the first comprehensive evaluation framework specifically tailored for assessing LLMbased WSD methods.RoDEval introduces four novel metrics: Disambiguation Scope, Disambiguation Robustness, Disambiguation Reliability, and Definition Generation Quality Score, enabling a multifaceted evaluation of LLMs' WSD capabilities.Experimental results using RoDEval across five mainstream LLMs uncover significant limitations in their WSD performance.Specifically, incorrect definition selections in multiple-choice WSD tasks stem not from simple neglect or forget of correct options, but rather from incomplete acquisition of the all senses for polysemous words.Instead, disambiguation reliability is often compromised by the models' persistent overconfidence.In addition, inherent biases continue to affect performance, and scaling up model parameters alone fails to meaningfully enhance their ability to generate accurate sense definitions.These findings provide actionable insights for enhancing LLMs' WSD capabilities.The source code and evaluation scripts are open-sourced at https: //github.com/DayDream405/RoDEval.

Kaiyuan Zhang, Qian Liu, Luyang Zhang, Chaoqun Zheng, Shuaimin Li, Bing Xu, Muyun Yang, Xinxiao Qiao, Wenpeng Lu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Argumentative essay generation (AEG) is a complex task that requires advanced semantic understanding, logical reasoning, and organized integration of perspectives.Despite showing a promising performance, current efforts often overlook the dynamical and hierarchical nature of structural argumentative planning, and struggle with flexible rhetorical expression, leading to limited argument divergence and rhetorical optimization.Inspired by human debate behavior and Bitzer's rhetorical situation theory, we propose a debate-driven rhetorical framework for argumentative writing.The uniqueness lies in three aspects: (1) it dynamically assesses the divergence of viewpoints and progressively reveals the hierarchical outline of arguments based on a depththen-breadth paradigm, improving the perspective divergence within argumentation; (2) simulates human debate through iterative defenderattacker interactions, improving the logical coherence of arguments; (3) incorporates Bitzer's rhetorical situation theory to flexibly select appropriate rhetorical techniques, enabling the rhetorical expression.Experiments on four benchmarks validate that our approach significantly improves logical depth, argumentative diversity, and rhetorical persuasiveness over existing state-of-the-art models 1 .* Corresponding authors. 1 Code and data are available at https://github.com/ zxg-x/DARE Social media affects attention and distracts people.Social media affects attention and distracts people.Social media affects attention and distracts people.Social media is a waste of time.Social media is a waste of time.Social media is a waste of time.

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU.

The International Classification of Diseases (ICD) coding assigns standardized codes to diseases. Automating this process enhances the efficiency and accuracy of clinical records processing. However, current methods struggle with noisy and lengthy clinical texts, making it difficult to ensure the reliability of feature extraction. Furthermore, they typically make separate binary predictions for each code, overlooking the dependencies between them. To address these issues, we propose a novel model called Hierarchical Feature Optimization and Rescorer (HiRes). We employ a cascaded convolution architecture to mitigate noise and enhance feature representation. Additionally, a masked autoencoder-based rescorer is introduced to capture ICD code interdependencies, refining initial predictions for improved accuracy. The model also considers the inconsistencies in code representations. Experiments on the MIMIC datasets demonstrate the effectiveness of our model.

Accurate diagnosis of Alzheimer’s disease is vital for effective treatment. Recently, a mainstream approach emerged that uses large language models (LLMs) to generate interpretable diagnosis. However, these methods face two significant challenges: (1) Incomplete Utilization of Raw Image Information: Converting images into text for LLMs input leads to the loss of the original image information. (2) Hallucination in LLMs: Diagnostic biases from LLMs hallucinations are neglected. To address these challenges, we propose a Medical Diagnosis Chain-of-Thought with Self-Diagnostic Refinement (MdCoT) framework. The MdCoT framework consists of two core modules: (1) Multimodal AD Diagnostic Chain-of-Thought: By including raw images as input, multimodal large language models (MLLMs) are allowed to capture fine-grained features, and (2) Self-Diagnostic Refinement: By guiding MLLMs to self-check and refine the diagnostic results, MdCoT achieves to mitigate hallucination. Experiments on widely used benchmarks demonstrate that MdCoT surpasses all baselines. Besides, extensive auxiliary experiments demonstrate the superiority of MdCoT.

Recently, Multimodal Named Entity Recognition (MNER) has attracted significant attention. Although MNER utilizing in-context learning has shown improved performance, modality retrieval bias often diminishes the relevance of in-context examples. To address this issue, we propose a self-relevance-based multimodal in-context learning method to mitigate modality retrieval bias by dynamically adjusting the weight of each modality. Specifically, we first measure the self-relevance of the query by calculating the similarity between textual and visual modalities, which helps to assess how much visual information contributes to the textual context. Then, we rank the similarity of different modalities, adjust the image rankings based on self-relevance to reduce modality retrieval bias, and integrate them to select the k most relevant examples. Finally, we use task definition and retrieved examples as effective guidance provided to the Multimodal Large Language Models to obtain feedback. Experimental results demonstrate that our method achieves SOTA performance on two benchmark datasets.

Few-shot knowledge graph reasoning (FS-KGR) try to infer missing facts in a knowledge graphs using limited data (such as only 3/5 samples).Existing strategies have shown good performance by mining more supervised information for few-shot learning through meta-learning and self-supervised learning. However, the problem of insufficient samples has not been fundamentally solved. In this paper, we propose a novel algorithm based on adversarial learning for Enhancing Negative samples in few-shot scenarios of FS-KGR, termed FS-KEN. Specifically, we are the first to use GAN to conduct data augmentation on FS-KGR scenario. FS-KEN uses policy gradient GANs for negative sample augmentation, solving the gradient back-propagation issue in traditional GANs. The generator aims to produce high-quality negative entities. while the objective of the discriminator is to distinguish between generated entities and real entities. Comprehensive experiments conducted on two few-shot knowledge graph completion datasets reveal that FS-KEN surpasses other baseline models, achieving state-of-the-art results.

Fine-tuning sequence-to-sequence (Seq2Seq) models applied on downstream datasets have gained remarkable success in the task of medical question summarization (MQS). However, Seq2Seq models suffer from a discrepancy between their objective function and evaluation metrics, whose objective function is based on local and token-level predictions whereas the evaluation metrics of MQS focus on overall similarity between the gold references and system predictions. To address the gap, it is crucial to consider multiple candidate summaries, assess their quality and re-rank them to obtain the optimal summary. In this paper, we propose to enhance MQS through re-ranking. Specifically, we introduce two re-rankers (SimGate and LLM) designed to perform reference-free evaluations on candidate summaries and select the best one. The former evaluates candidate summaries using text semantic similarity and a confidence gate, while the latter leverages the powerful comprehension capability of large language models to identify more preferable summaries. Experimental results demonstrate the effectiveness of the proposed re-ranking mechanisms. The SimGate re-ranker, compared with BART, exhibits a significant improvement in the ROUGE score on all datasets. Additionally, LLM re-rankers also demonstrate significant improvements on most datasets, underscoring the promising potential of large language models as re-rankers. The code and datasets are available at https://github.com/yrbobo/MQS-Reranker.

The remarkable prompting capability of large language models (LLMs) offers substantial convenience to users across diverse backgrounds. Nevertheless, as the sensitive information within prompts is inevitably exposed to LLMs, caution must be exercised to preserve privacy. Among various studies, text anonymization is considered an effective approach to preventing privacy leakage in prompts through text substitution. However, existing works overemphasize privacy while overlooks preserving contextual integrity, degrading semantic consistency. To address these concerns, this paper introduces a context-sensitive prompt privacy-preserving framework, namely Adaptive Linguistic Sanitization and Anonymization (ALSA). In specific, ALSA incorporates a three-dimensional scoring mechanism to dynamically quantify the substitutability of each word within a prompt by integrating the Privacy Leakage Risk Score (PLRS), the Contextual Information Importance Score (CIIS), and the Task Relevance Score (TRS). Subsequently, a clustering technique is adopted to dynamically determine the threshold for assigning an anonymization action (i.e., Retain, Replace, Encrypt, or Delete) by balancing privacy, semantics, and task relevance. Extensive experiments on five benchmark datasets validate the superiority of ALSA over state-of-the-art baselines in terms of accuracy, privacy preservation, and semantic integrity.

Deep graph clustering (DGC) for attribute-missing graphs is an unsupervised task aimed at partitioning nodes with incomplete attributes into distinct clusters. Existing imputation methods for attribute-missing graphs often fail to account for the varying amounts of information available across node neighborhoods, leading to unreliable results. To address this issue, we propose a novel method named Divide-Then-Rule Graph Completion (DTRGC). This method first addresses nodes with sufficient known neighborhood information and treats the imputed results as new knowledge to iteratively impute more challenging nodes, while leveraging clustering information to correct imputation errors. Specifically, Dynamic Cluster-Aware Feature Propagation initializes missing node attributes by adjusting propagation weights based on the clustering structure. Subsequently, Hierarchical Neighborhood-Aware Imputation categorizes attribute-missing nodes into three groups based on the completeness of their neighborhood attributes. The imputation is performed hierarchically, prioritizing the groups with nodes that have the most available neighborhood information. The cluster structure is then used to refine the imputation and correct potential errors. Finally, Hop-wise Representation Enhancement integrates information across multiple hops, thereby enriching the expressiveness of node representations. Experimental results on 6 widely used graph datasets show that DTRGC significantly improves the clustering performance of various DGC methods under attribute-missing graphs.

Medication recommendation aims to suggest personalized drug combinations to patients based on their longitudinal medical histories stored in electronic health record (EHR) datasets. Patients' Dynamic Treatment Regimes (DTRs) determine how patients' drug combinations change along with the evolution of disease treatment. DTRs are effective for comprehending disease-treatment dynamics and for recommending a timely and personalized combination of medications for patients. However, existing medication recommender systems (MRSs) overlook the multiple treatment pathways generated by the intervention of DTRs and can only recommend a single treatment paradigm, ignoring the fact that patients may be at different treatment stages and thus require different treatment regime. Such disregard leads to a significant limitation in recommending personalized medication combinations tailored to different treatment stages, yielding greatly compromised accuracy and applicability of MRSs. Moreover, existing methods often overlook the time interval information over patients' successive visits, which is critical to indicate patients' treatment evolution. To address these significant gaps, we propose a Time-aware Medication Recommendation Framework via Intervention of Dynamic Treatment Regimes, called MR-DTR. To explicitly illustrate the intervention processes of DTRs on similar patients, we employ a co-guided graph to connect various patient sequences. In addition, to fully utilize the time interval information, we design a time-aware guidance mechanism dedicated to the co-guided graph to efficiently learn medication representation using the patient's guidance information. We also introduce relative time intervals in the encoder to act as positional information. Extensive experiments on two real-world datasets demonstrate that MR-DTR surpasses state-of-the-art models in terms of recommendation performance. Our code is available at: https://github.com/liyifo/MR-DTR.

Traffic forecasting plays a crucial role in establishing an Intelligent Transportation System (ITS) by providing essential insights. Existing traffic forecasting relies on the assumption that there is a hidden invariant spatial-temporal pattern in the large-scale dataset. However, the traffic patterns are easily influenced by many unpredictable external factors, such as policy interventions and climate changes. Due to the dynamic nature of these exogenous factors, the traffic network's spatial-temporal patterns are also changed, thus impacting the performance of traffic forecasting models. Thus, there is an urgent need to rethink the traffic forecasting model in a fast-adaptive manner. To solve this challenge, this paper proposes an Adaptive Spatio-Temporal Context Learning framework named ASTCL, which achieves desired forecasting accuracy using daily basis traffic data collected from dozens of sensors. ASTCL constructs adaptive spatio-temporal contexts for target locations in the traffic network and generates dynamic sequence graphs based on semantic similarities. The adaptive contexts aggregate valuable information from available data, while the graphs reveal dynamic trends in traffic properties. Further, ASTCL introduces a joint convolution and attention mechanism to model intricate spatio-temporal relationships from multiple perspectives. Extensive experiments conducted on four real-world datasets demonstrate that ASTCL achieves remarkable fast adaptability and outperforms other state-of-the-art methods by a significant margin.

Multi-modal hashing achieves low storage costs and high retrieval speeds by using compact hash codes to represent complex and heterogeneous multi-modal data, effectively addressing the inefficiency and resource intensiveness challenges faced by the traditional multi-modal retrieval methods. However, balancing intraclass compactness and interclass separability remains a struggle in existing works due to coarse-grained feature limitations, simplified fusion strategies that overlook semantic complementarity, and neglect of the structural information within the multi-modal data. To address these limitations comprehensively, we propose a Proto-centric Multi-modal Hashing with Pronounced Category Differences (PMH-PCD) model. Specifically, PMH-PCD first learns modality-specific prototypes by deeply exploring within-modality class information, ensuring effective fusion of each modality's unique characteristics. Furthermore, it learns multi-modal integrated class prototypes that seamlessly incorporate semantic information across modalities to effectively capture and represent the intricate relationships and complementary semantic content embedded within the multi-modal data. Additionally, to generate more discriminative and representative binary hash codes, PMH-PCD integrates multifaceted semantic information, encompassing both low-level pairwise relations and high-level structural patterns, holistically capturing intricate data details and leveraging underlying structures. The experimental results demonstrate that, compared with existing advanced methods, PMH-PCD achieves superior and consistent performances in multi-modal retrieval tasks. To promote further research and reproducibility, we have publicly released the source code of PMH-PCD at https://github.com/vindahi/PMH-PCD.

Efficient code search techniques are crucial in accelerating software development by aiding developers in locating specific code snippets and understanding code functionalities. This study investigates code search methodologies, focusing on the emerging significance of semantic consistency in data augmentation techniques. While existing approaches predominantly enhance raw data, often requiring additional preprocessing and incurring higher training costs, this research introduces a pioneering method operating at the code and query representation levels. By bypassing the need for extensive data processing, this novel approach fosters an interactive alignment between code and query, augmenting the semantic coherence crucial for effective code search. An extensive empirical evaluation of a diverse dataset across multiple programming languages substantiates the efficacy of this approach in significantly enhancing code search model performance compared to traditional methodologies. The implementation is publicly available on GitHub, 1 offering an accessible resource for further exploration and application.

Session-based Recommender Systems (SBRSs) aim to recommend the next item to users based on their historical interactions with items within or between sessions. A session is constituted by a sequence of interactions between the user and items within a continuous period. Existing SBRSs often focus on modeling co-occurrence-based inter-item transitions within or between sessions only. They generally overlook intrinsic inter-item semantic relations. Specifically, in practice, many items are substitutable or complementary to each other. Such relations provide significant signals to guide user interaction behaviors as well as the next-item recommendations. Moreover, existing works overlook the fact that user behaviors are driven simultaneously by both user intent and item attributes, failing to consider the implicit item characteristics embedded within. Such practice leads to entangled user intent and latent item characteristics, bringing unnecessary interference between these two aspects, impeding accurate modeling of each aspect, ultimately significantly impeding recommendation performance. To bridge these gaps, we propose a novel framework called S emantic relation guided dual-view C ontrastive L earning for S ession-based R ecommendations (SCL-SR). SCL-SR introduces a novel semantic relation-guided contrastive learning module to capture additional supervision signals from both user intent view and item attribute view to guide the next-item prediction better. Then, we propose a novel intent-attribute disentangler to effectively mitigate the interference between user intent and latent item characteristics for further improving the recommendation performance. Extensive experiments on three real-world datasets demonstrate the significant superiority of SCL-SR over the state-of-the-art approaches, including achieving substantial improvements ranging from 7.10% to 12.82% on the Tmall dataset. Our source code and datasets are available at https://github.com/Nishikata97/SCL-SR .

Multi-modal sarcasm detection involves determining whether a given multi-modal input conveys sarcastic intent by analyzing the underlying sentiment. Recently, vision large language models have shown remarkable success on various of multi-modal tasks. Inspired by this, we systematically investigate the impact of vision large language models in zero-shot multi-modal sarcasm detection task. Furthermore, to capture different perspectives of sarcastic expressions, we propose a multi-view agent framework, S 3 Agent, designed to enhance zero-shot multi-modal sarcasm detection by leveraging three critical perspectives: superficial expression , semantic information , and sentiment expression . Our experiments on the MMSD2.0 dataset, which involves six models and four prompting strategies, demonstrate that our approach achieves state-of-the-art performance. Our method achieves an average improvement of 13.2% in accuracy. Moreover, we evaluate our method on the text-only sarcasm detection task, where it also surpasses baseline approaches.

With the growing complexity of fact verification tasks, the concern with "thoughtful" reasoning capabilities is increasing.However, recent fact verification benchmarks mainly focus on checking a narrow scope of semantic factoids within claims and lack an explicit logical reasoning process.In this paper, we introduce CHECKWHY, a challenging dataset tailored to a novel causal fact verification task: checking the truthfulness of the causal relation within claims through rigorous reasoning steps.CHECKWHY consists of over 19K "why" claimevidence-argument structure triplets with supports, refutes, and not enough info labels.Each argument structure is composed of connected evidence, representing the reasoning process that begins with foundational evidence and progresses toward claim establishment.Through extensive experiments on state-of-the-art models, we validate the importance of incorporating the argument structure for causal fact verification.Moreover, the automated and human evaluation of argument structure generation reveals the difficulty in producing satisfying argument structure by fine-tuned models or Chainof-Thought prompted LLMs, leaving considerable room for future improvements 1 .

Drug-target binding affinity prediction is critical to drug design. Some existing computational methods rely on single-scale data and cannot fully integrate the rich information of multi-scale data, such as molecular structures and network information. In this paper, we propose the MBC-DTA model, which effectively integrates multi-scale data, and models the complex interactions between atoms and amino acids. We introduce GCN and GAT, which effectively extract the feature representation of molecular structure scale and network scale. Afterwards, the features obtained from the molecular structure scale are fed into a bilinear attention network, which captures the intricate interaction information between drug-target pairs. Additionally, a cross-scale graph contrastive learning strategy is applied, optimizing the feature representations across different scales. Extensive experimental results on two benchmark datasets demonstrate that the MBC-DTA model outperforms existing state-of-the-art methods.

Electronic health records (EHRs) play a crucial role in the development of personalized treatment plans for patients. However, EHRs are often highly incomplete, posing significant challenges for predictive modeling. While existing deep learning models employ various imputation techniques to reconstruct missing values, they often fail to represent missing data in a personalized manner and do not learn from the missingness patterns in EHRs data. This limitation reduces their effectiveness in practical personalized healthcare applications. To address this issue, we propose SPIME, a self-supervised model that generates personalized imputations in EHRs data for patient health status prediction. We introduce a personalized missing mask (PMM) based on the frequency of feature measurements. Additionally, we incorporate a masked imputation task (MIT) loss that minimizes the loss of artificially introduced missing values, thereby enhancing the model’s capability to handle missing data. SPIME adopts self-supervised pretraining to learn representations from personalized missing patterns and reconstructs missing data in the latent space. To further enhance representation learning, two independent attention mechanisms are applied separately across the feature and temporal dimensions. Experimental results on two real-world EHRs datasets show that SPIME outperforms existing state-of-the-art methods in predicting in-hospital mortality and decompensation, demonstrating its effectiveness in reconstructing missing data and predicting patient health status. The code will be published at https://github.com/cling6666/SPIME.

With the development of the Intelligent Transportation Systems, a great deal of work has been proposed to tackle traffic prediction tasks. Despite their good performance, most traffic prediction models are point estimation models, lacking the capability to estimate the uncertainties of future traffic data, which is crucial in practical traffic decision-making. Aiming at this problem, we combine the probabilistic estimation capabilities of conditional normalizing flows with the spatio-temporal relationship learning of spatio-temporal graphs, leading to a Spatio-Temporal Graph Normalizing Flow (STGNF) model to estimate the distribution of future traffic data. We are the first to employ the conditional normalizing flows as the backbone for probabilistic traffic prediction. Then we design a spatio-temporal graph conditional fusion network to learn the spatio-temporal relationships between future and historical traffic data, which are provided to the conditional normalizing flows as conditional information. Extensive experiments on two real-world traffic datasets demonstrate that our proposed model significantly outperforms the state-of-the-art baselines.

The inherent complexity of real-world time series data, combined with the cost and infeasibility of manual labeling, presents considerable challenges to time series representation learning. Most existing studies tend to utilize data augmentation techniques to construct positive and negative samples and leverage a comparative learning framework to generate time series representations. However, they typically employ simple data augmentation techniques, such as jitter and cropping, to construct positive samples while randomly selecting irrelevant samples as negative ones, which are easily distinguished and unable to guide comparative learning to capture subtle discriminative features. Furthermore, they usually employ only a single positive sample for comparative learning, which is insufficient to model the diversity and hurts the robustness. To address these issues, this paper proposes a Time Series representation learning framework via Dual Reference Contrasting (TS-DRC). Specifically, we first utilize Markov transition field or Gramian angular field to transform the anchor sample of time series into image representations, which are adopted as positive samples. Then, we incorporate two positive samples (dual references) and one negative sample into the comparative learning framework, and devise a novel optimization objective to guide the model to capture more discriminate features, mitigate overfitting, and enhance the robustness. Extensive experiments conducted on four public real-world datasets demonstrate that our TS-DRC outperforms other state-of-the-art baselines.Our code is available at: https://github.com/yurui12138/TS-DRC.

Medical entity disambiguation (MED) plays a crucial role in natural language processing and biomedical domains, which is the task of mapping ambiguous medical mentions to structured candidate medical entities from knowledge bases (KBs). However, existing methods for MED often fail to fully utilize the knowledge within medical KBs and overlook essential interactions between medical mentions and candidate entities, resulting in knowledge- and interaction-inefficient modeling and suboptimal disambiguation performance. To address these limitations, this paper proposes a novel approach, MED with Medical Mention Relation and Fine-grained Entity Knowledge (MMR-FEK). Specifically, MMR-FEK incorporates a mention relation fusion module and an entity knowledge fusion module, followed by an interaction module. The former employs a relation graph convolutional network to fuse mention relation information between medical mentions to enhance mention representations, while the latter leverages an attention mechanism to fuse synonym and type information of candidate entities to enhance entity representations. Afterwards, an interaction module is designed to employ a bidirectional attention mechanism to capture interactions between mentions and entities to generate the matching representation. Extensive experiments on two publicly available real-world datasets demonstrate MMR-FEK’s superiority over state-of-the-art(SOTA) MED baselines across all metrics. Our source code is publicly available.

The goal of medication recommendation system is to recommend appropriate pharmaceutical interventions based on a patient’s diagnosis. Most of existing approaches often formulate these recommendations use data on diagnoses, procedures, and prescriptions accumulated in the electronic health records (EHR), and despite the great successes, they seem to have limitations on modelling the significance of medication to a patient’s current visit and mining fine-grained medication representation information. To address these issues, we propose a novel Significanceaware Medication Recommendation (SMRec) framework built on significance of medication to patients and fine-grained medication representation learning. Specifically, we first design a encoding mechanism to compute significance information of medications for each patient’s visit. Then, we utilize the set-level medication co-occurrence graph based on patients’ medical history which integrates temporal dependency to learn fine-grained medication representations. Experimental results on the publicly available MIMIC-III dataset demonstrate the superior effectiveness of our model compared to other approaches1.

Drug-target interaction (DTI) prediction is a critical step in drug discovery. Deep learning has shown great potential in DTI prediction. In recent years, many sequence-based DTI prediction methods have been proposed. However, the current methods do not fully represent drugs and proteins and ignore the local and global features of these molecules. In response to these challenges, we propose a sequence-based CNN and Transformer collaborative prediction method (SCTDTI) for drug-target interaction. We train and evaluate our proposed approach on two public drug-target datasets, and experimental results show that SCTDTI improves DTI prediction performance compared to state-of-the-art baselines.

Most Seq2Seq neural model-based medical question summarization (MQS) systems have a severe mismatch between training and inference, i.e., exposure bias. However, this problem remains unexplored in the MQS task. To bridge this research gap and alleviate the problem of exposure bias, we propose a novel re-ranking training framework for MQS called Multi-view Contrastive Learning (MvCL). MvCL simultaneously considers the similarity scores between medical questions and candidate summaries as well as the average similarity scores between candidate summaries and other candidates within the same group, and utilizes contrastive learning to optimize the model’s ranking ability. Additionally, we propose a new multilevel inference approach to adapt to this training strategy. The approach first filters out candidate summaries that are dissimilar to the original medical question, and then selects the summary with the highest average similarity to other candidate summaries from the remaining candidates as the final output. We conducted extensive experiments, and the results demonstrate that our proposed MvCL framework achieves state-of-the-art results on the majority of evaluation metrics across four datasets.1

Sequential diagnosis prediction (SDP) is a complex and challenging task, aming to predict future diagnoses of patients by analyzing their historical medical records. Although graph neural networks(GNNs) has been applied to successfully address the challenge of heterogeneous data integration in electronic health records, relatively limited work has been done on GNNs for sequential diagnosis prediction. Graph neural network-based methods, aimed at capturing structural and relational patterns of EHR data for sequential diagnosis prediction, explore code-code pairwise relationships, resulting in an inability to learn fine-grained, higher-order interaction relationships among different types medical codes. As a result, they are difficult to effectively model complex, multi-dimensional interactions among different types of medical codes necessary for accurate and nuanced diagnosis predictions. To address these challenges, this paper proposes a novel approach called Multi-Channel Hypergraph Network (MCHN) predictive framework for sequential diagnosis prediction. The proposed method aims to explore the fine-grained higher-order interactions between different types of medical codes via multi-channel hypergraphs. Specifically, MCHN learns two levels of code embeddings from multi-channel hypergraph learning module and line graph learning module, respectively: (i) multi-channel hypergraph learning module, which is to learn multi-channel hypergraph level code embeddings by modeling the higher-order relationships between medical codes in different hypergraphs; and (ii) line graph learning module, which is to learn the line graph level code embeddings by modeling code-code pairwise relationships. In MCHN, we propose a novel channel-level attention mechanism to help our model attend to the informativeness of the different channel for forecasting future patient diagnoses. We also design a code-level attention mechanism, which can to pay more attention to the medical codes that are more important to the visit representation. Moreover, MCHN aggregates the learnt code embeddings in the two levels to generate the visit representation, which is used to predict the patient’s next diagnosis. Experimental results on two benchmark datasets consistently demonstrate that MCHN outperforms state-of-the-art methods1.

Traditional Chinese Medicine (TCM) is a natural, safe, and effective therapeutic approach with widespread application worldwide. The unique diagnostic methods of TCM often require a comprehensive analysis of patient information, much of which is contained in clinical text. Numerous studies have demonstrated the effectiveness of natural language processing (NLP) techniques in TCM disease classification. Therefore, this paper focuses on the task of TCM syndrome differentiation, proposing a novel matching score calculation method and a new label attention calculation method to assist the model in focusing on the relationship between TCM syndrome and disease symptom. Specifically, we enhance the model’s attention to the uniqueness of the relationship between TCM syndrome and symptom by introducing a finer-grained token-level matching score. Simultaneously, we improve the model’s attention to the generality of the relationship between TCM syndrome and symptom through a more global label attention mechanism. Additionally, we observe a severe long-tail problem in the dataset. To alleviate this issue, we propose the use of focal loss to help the model pay more attention to challenging samples. Extensive experiments on the TCM-SD dataset indicate that our approach significantly outperforms state-of-the-art baselines1.

Sequential recommendation has been developed to predict the next item in which users are most interested by capturing user behavior patterns embedded in their historical interaction sequences. However, most existing methods appear to exhibit limitations in modeling fine-grained dependencies embedded in users’ various periodic behavior patterns and heterogeneous dependencies across multi-behaviors. Towards this end, we propose a Filter-enhanced Hypergraph Transformer framework for Multi-Behavior Sequential Recommendation (FHT-MB) to address the above challenges. Specifically, a multi-scale filter layer equipped with multi-learnable filters is devised to encode behavior-aware sequential patterns emerging from different periodic trends (e.g., daily or weekly routines), and then a hypergraph structure is devised to extract heterogeneous dependencies across users’ multiple types of behaviors. Extensive experiments on two real-world e-commerce datasets show the superiority of our proposed FHT-MB over various state-of-the-art methods.1

Cross-modal hashing is favored in the field of large-scale cross-modal retrieval for its fast query and low storage cost. Existing cross-modal hashing methods are typically based on an idealized assumption that data from different modalities are fully and completely paired. However, in practical scenarios, the occurrence of missing modal data is common due to technical difficulties, hardware failures, and challenges in data collection, contradicting the aforementioned assumption. In this paper, we propose an innovative unsupervised cross-modal hashing frame-work, named Semantic Reconstruction Guided Missing Hashing (SRGMH). Specifically, we utilize Dual-Variational Autoencoders (D-VAEs) to map features of different modalities into a shared low-dimensional latent representation, better bridging the gaps between modalities. Notably, we generate pseudo-representations of other modalities corresponding to the missing modality, effectively solving the problem of missing modal data. Moreover, we construct a refined adjacency similarity matrix to align the latent representations of different modalities, enhancing the quality of completed data and ensuring semantic consistency across modalities. Finally, we embed the adjacency similarity matrices in a shared latent representation space to jointly learn hash functions and hash codes, which enriches the semantic content and maintains structural similarity between hash functions and codes. Experiments on three real-world datasets demonstrate the superior performance of the proposed method on both retrieval accuracy and efficiency.

By summarizing longer consumer health questions into shorter and essential ones, medical question-answering systems can more accurately understand consumer intentions and retrieve suitable answers. However, medical question summarization is very challenging due to obvious distinctions in health trouble descriptions from patients and doctors. Although deep learning has been applied to successfully address the medical question summarization (MQS) task, two challenges remain: how to correctly capture question focus to model its semantic intention, and how to obtain reliable datasets to fairly evaluate performance. To address these challenges, this article proposes a novel medical question summarization framework based on e ntity-driven c ontrastive l earning (ECL). ECL employs medical entities present in frequently asked questions (FAQs) as focuses and devises an effective mechanism to generate hard negative samples. This approach compels models to focus on essential information and consequently generate more accurate question summaries. Furthermore, we have discovered that some MQS datasets, such as the iCliniq dataset with a 33% duplicate rate, have significant data leakage issues. To ensure an impartial evaluation of the related methods, this article carefully examines leaked samples to reorganize more reasonable datasets. Extensive experiments demonstrate that our ECL method outperforms the existing methods and achieves new state-of-the-art performance, i.e., 52.85, 43.16, 41.31, 43.52 in terms of ROUGE-1 metric on MeQSum, CHQ-Summ, iCliniq, HealthCareMagic dataset, respectively. The code and datasets are available at https://github.com/yrbobo/MQS-ECL

Community detection is an important task in graph analysis, and it is of great significance in reality. Recently, unsupervised learning has been widely used in community detection tasks. However, only a few community detection models combine unsupervised learning with graph neural networks (GNNs). To this end, in this paper, we combine GNNs with unsupervised learning to propose a new model, Unsupervised graph neural network with Self-expressive attention for Community detection (USCom). We first use the graph attention encoder to generate node embeddings. Then we apply the self-expressive principle to optimize the node embeddings to make them more suitable for community detection tasks. Finally, we utilize a four-layer perceptron for community detection. The experimental results show that the model proposed in this paper outperforms the comparison baselines on community detection tasks.

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to overfit to seen classes, failing to generalize to unseen classes. In this paper, we propose a Knowledge-Aware Prompt Tuning (KAPT) framework for vision-language models. Our approach takes the inspiration from human intelligence in which external knowledge is usually incorporated into recognizing novel categories of objects. Specifically, we design two complementary types of knowledge-aware prompts for the text encoder to leverage the distinctive characteristics of category-related external knowledge. The discrete prompt extracts the key information from descriptions of an object category, and the learned continuous prompt captures overall contexts. We further design an adaptation head for the visual encoder to aggregate salient attentive visual cues, which establishes discriminative and task-aware visual representations. We conduct extensive experiments on 11 widely-used benchmark datasets and the results verify the effectiveness in few-shot image classification, especially in generalizing to unseen categories. Compared with the state-of-the-art CoCoOp method, KAPT exhibits favorable performance and achieves an absolute gain of 3.22% on new classes and 2.57% in terms of harmonic mean.

Sequential diagnosis prediction (SDP) is a challenging task, aiming to predict patients’ future diagnoses based on their historical medical records. While methods based on graph neural networks (GNNs) have proven successful for this task, they typically focus on modeling pairwise diseases using a global disease combination graph. However, these approaches neglect the fine-grained higher-order relations among persistent and emerging diseases within a single visit, which may contain crucial clues to predict the next diagnosis. Additionally, they fail to fully leverage patient-related clinical information present in electronic health records (EHRs). To address these challenges, this paper proposes a novel approach called the fusion of Dynamic Hypergraph and Clinical Event (DHCE) for sequential diagnosis prediction. The proposed method aims to exploit the fine-grained higher-order relations among diagnoses within a visit and leverage clinical event information from EHRs to improve the accuracy of predicting the next diagnosis. Specifically, DHCE categorizes diagnoses within a single visit in a fine-grained granularity into persistent and emerging categories based on a patient’s historical diagnoses. It then constructs dynamic hypergraphs to capture higher-order disease relations within each visit. Next, we design a transition function to extract the transitional context from previous visits in order to generate the visit representation. Furthermore, to fully leverage patient-related clinical events in a visit, we utilize Bio-Clinical BERT to encode them and generate the clinical event representation for each visit. Finally, we combine the visit representation and event representation to generate a comprehensive patient representation, which is then used to predict the patient’s next diagnosis. Experimental results on two benchmark datasets consistently demonstrate that DHCE outperforms state-of-the-art methods1.

Drug-drug interaction (DDI) has been a challenging problem in healthcare machine-learning research. DDI might cause changes in drug pharmacological activity and trigger adverse patient reactions. Therefore, it is critical for both patients and society to effectively identify potential DDI. Most recent studies have used graph-based learning methods to predict DDI, but these methods usually have the following limitations: i) modeling drug information on a single view; ii) ignoring the importance of different neighboring nodes; and iii) failing to integrate the drug-embedded information well. Therefore, this paper proposes a multi-view feature fusion strategy based on graph attention networks(MV-GAT). In MV-GAT, we use the graph representation learning method of bond-aware message passing neural network to obtain the local features of each atom in the molecular graph and the global features of the molecular graph. Meanwhile, We propose an attention mechanism based on a fusion strategy to handle the fusion of drug features and topological information under each view, which can efficiently integrate the features extracted from molecular and interaction maps. In addition, to ensure the diversity of node features, we use an unsupervised contrastive learning component in each Graph Neural Networks (GNN) layer to address the over-smoothing problem during information transfer. Comprehensive experiments on multiple real datasets show that MV-GAT has good generalization performance.

Privacy image classification (PIC) has attracted increasing attention as it can help people make appropriate privacy decisions when sharing images. Most recently, some pioneer research efforts have been made to utilize multimodal information for PIC, since multi-modality can provide richer information than single modality. Those research efforts on multimodal PIC are under the assumption of independently identically distribution. However, connections between different modalities commonly exist in real-world cases. Taking the modalities of scene and object as example, in the scene of ’library/indoor’, the object ’book jacket’ resides with high probabilities. To this end, in this paper, a novel PIC approach, called CoupledPIC, is proposed to bridge this gap by comprehensively capturing the coupling relations between different modalities. In CoupledPIC, two submodules are designed to capture explicit and implicit coupling relations between different modalities respectively. The explicit modality coupling is learned with a tensor fusion networks based submodule, via the direct interaction of features. For the implicit modality coupling, a graph convolutional networks based submodule is proposed to learn on both the initial graphs and attention guided graphs, via information aggregation on graphs. Extensive experiments on the public benchmark, PicAlert, demonstrate the effectiveness of the proposed CoupledPIC, yielding significant improvement by modeling inter-modality coupling information.

Word sense disambiguation (WSD), identifying the most suitable meaning of ambiguous words in the given contexts according to a predefined sense inventory, is one of the most classical and challenging tasks in natural language processing. Benefiting from the powerful ability of deep neural networks, WSD has achieved a great advancement in recent years. Reformulating WSD as a text span extraction task is an effective approach, which accepts a sentence context of an ambiguous word together with all definitions of its candidate senses simultaneously, and requires to extract the text span corresponding with the right sense. However, the approach merely depends on a short definition to learn sense representation, which neglects abundant semantic knowledge from related senses and leads to data-inefficient learning and suboptimal WSD performance. To address the limitations, we propose a novel WSD method with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension (KELESC). Specifically, a knowledge-enhanced method is proposed to enrich semantic representation by incorporating additional examples and definitions of the related senses in WordNet. Then, in order to avoid the huge computing complexity induced by the additional information, a local self-attention mechanism is utilized to constrain attention to be local, which allows longer input texts without large-scale computing burdens. Extensive experimental results demonstrate that KELESC achieves better performance than baseline models on public benchmark datasets.

Next basket recommender systems (NBRs) aim to recommend a user’s next (shopping) basket of items via modeling the user’s preferences towards items based on the user’s purchase history, usually a sequence of historical baskets. Due to its wide applicability in the real-world E-commerce industry, the studies NBR have attracted increasing attention in recent years. NBRs have been widely studied and much progress has been achieved in this area with a variety of NBR approaches having been proposed. However, an important issue is that there is a lack of a systematic and unified evaluation over the various NBR approaches. Different studies often evaluate NBR approaches on different datasets, under different experimental settings, making it hard to fairly and effectively compare the performance of different NBR approaches. To bridge this gap, in this work, we conduct a systematical empirical study in NBR area. Specifically, we review the representative work in NBR and analyze their cons and pros. Then, we run the selected NBR algorithms on the same datasets, under the same experimental setting and evaluate their performances using the same measurements. This provides a unified framework to fairly compare different NBR approaches. We hope this study can provide a valuable reference for the future research in this vibrant area.

A session-based news recommender system recommends the next news to a user by modeling the potential interests embedded in a sequence of news read/clicked by her/him in a session. Generally, a user’s interests are diverse, namely there are multiple interests corresponding to different types of news, e.g., news of distinct topics, within a session. However, most of existing methods typically overlook such important characteristic and thus fail to distinguish and model the potential multiple interests of a user, impeding accurate recommendation of the next piece of news. Therefore, this paper proposes multi-interest news sequence (MINS) model for news recommendation. In MINS, a news encoder based on self-attention is devised on learn an informative embedding for each piece of news, and then a novel parallel interest network is devised to extract the potential multiple interests embedded in the news sequence in preparation for the subsequent next-news recommendations. The experimental results on a real-world dataset demonstrate that our model can achieve better performance than the state-of-the-art compared models. Our source code is publicly available on GitHub1.

COVID-19 has become a worldwide epidemic. Prediction of COVID-19 is an effective way to control its spread. Recently, some research efforts have made great progress on this task. However, these works rarely combine both the temporal and spatial domains for case number prediction. Moreover, most of them are only suitable for short-term prediction tasks, which cannot achieve good long-term predicting effects. Therefore, we use a method that combines human-mobility factors and time-series factors - the Spatio-temporal convolutional network (G-TCN) to deal with these problems. Firstly, we use data on the mobility of people between regions to generate graphs of regional relationships. Secondly, to process the spatial information at each moment, we apply multi-layer graph convolutional neural networks (GCNs) to aggregate multi-layer neighborhood information. And we input the information obtained by GCNs at different moments into temporal convolutional networks (TCNs), which are used to process the time-series information. Finally, we tested the proposed G-TCN method using datasets from four countries. The experimental results show that G-TCN has lower prediction errors than other comparison methods and can better fit the trend of COVID-19 development.

Text generation is crucial for many applications in natural language processing. With the prevalence of deep learning, the encoder-decoder architecture is dominantly adopted for this task. Accurately encoding the source information is of key importance to text generation, because the target text can be generated only when accurate and complete source information is captured by the encoder and fed into the decoder. However, most existing approaches fail to effectively encode and learn the entire source information, as some features are easy to be missed along with the encoding procedures of the encoder. Similar problems also confuse the implementation of the decoder. How to reduce the problem of information loss in the encoder-decoder model is critical for text generation. To address this issue, we propose a novel correlation encoder-decoder model, which optimizes both the encoder and the decoder to reduce the problem of information loss by enforcing them to minimize the differences between hierarchical layers by maximizing the mutual information. Experimental results on two benchmark datasets demonstrate that the proposed model substantially outperforms the existing state-of-the-art methods. Our source code is publicly available on GitHub1.

Chinese sentence matching is a critical and yet challenging task in natural language processing. Recent work on modeling sentence semantic relations with deep neural models has shown its great potential in improving the performance of sentence matching. However, existing sentence matching methods usually focus on generating word-level sentence representation, which neglects the character-level information and leads to weak semantic representations. Also, they usually capture the interactive features with an attention-based alignment, which are typically implemented on sentence level and neglect the interactions among characters, words and sentences. This paper proposes a novel Chinese sentence matching model with Multiple Alignments and Feature Augmentation (MAFA). Specifically, the model first employs the multi-level embedding layer to accept the character and word sequences of sentences, and introduces the multiple alignment layer to capture the interactions among characters, words and sentences in turn. Then, the feature augmentation layer is applied to combine the interactive features to generate the final semantic matching representations. Finally, the prediction layer is utilized to judge the matching degree of the input sentences. Substantial and extensive experiments are conducted on two real-world data sets to show that MAFA significantly outperforms the competing methods and achieve comnarable nerformance with BERT-based methods.

Intelligent human-device interfaces play key roles in fully automated vehicles (FAVs), ensuring smooth interactions and improving the driving experience. Listening to news is a popular method of relaxing during a journey; as a result, travelers require automatic recommendations of preferred news programs. Most existing news recommender systems usually learn topic-level representations of users and news for recommendations while neglecting to learn more informative aspect-level features, resulting in limited recommendation performance. To bridge this significant gap, we propose a novel Aspect-driven News Recommender System (ANRS) built on aspect-level user preferences and news representation learning. In ANRS, a news aspect-level encoder and a user aspect-level encoder are devised to learn the fine-grained aspect-level representations of users’ preferences and news characteristics respectively. These representations are subsequently fed into a click predictor to predict the probability of a given user clicking on the candidate news item. Extensive experiments demonstrate the superiority of our method over state-of-the-art baseline methods.

Session-based recommendations (SBR) play an important role in many real-world applications, such as e-commerce and media streaming. To perform accurate session-based recommendations, it is crucial to capture both sequential dependencies over a sequence of adjacent items and complex item transitions over a set of items within sessions. Note that item transitions are not necessarily dependent on sequential dependencies, e.g., the transition from one item to the other distant item in a session is often not sequential. However, almost all the existing session-based recommender systems (SBRS) fail to consider both kinds of information, which leads to their limited performance improvement. Aiming at this deficiency, we propose a novel sequential dependency enhanced graph neural network (SDE-GNN) to capture both sequential dependencies and item transition relations over items within sessions for more accurate next-item recommendations. Specifically, we first devise a sequential dependency learning module to capture the sequential dependencies over a sequence of adjacent items in each session. Then, we propose an item transition learning module to capture complex transitions between items. In the module, a novel residual gate and a specialized attention mechanism are integrated into gate-GNN to build an attention augmented GNN, called AU-GNN. Finally, we devise a gated fusion component to combine the learned sequential dependencies and item transitions together in preparation for the subsequent next-item recommendations. Exhaustive experiments on two public real-world data sets demonstrate the superiority of SDE-GNN over the state-of-the-art methods.

As a fundamental task in natural language processing, sentence semantic matching (SSM) is critical yet challenging due to difficulties in learning expressive sentence representation while capturing complex interactions between sentences. Recent work has shown the great potential of deep neural models in improving the performance of SSM task. However, existing work usually employs recurrent neural networks (RNNs) or 1D (one-dimensional) convolutional neural networks (CNNs) to learn sentence representation, leading to limited performance improvement. Benefiting from the multi-dimensional structure, 2D convolutional neural networks are expected to be more powerful to learn expressive sentence representation by capturing the implicit inter-sentence interactions and thus can further improve the performance of SSM. To this end, in this paper, we propose a novel sentence semantic matching model named Hierarchical CNN based on Dimension-augmented Representation (HiDR). In HiDR, first, bidirectional long short-term memory networks (LSTMs) are utilized to generate dimension-augmented representation for each of the input sentences; then, a hierarchical 2D CNN is devised to learn sentence representation while capturing the inter-sentence interactions, followed by a prediction layer based on sigmoid function to output the matching degree between sentences. To evaluate the performance of our proposed model, we conducted extensive experiments on two public real-world data sets. The empirical results show that HiDR has achieved remarkable results, which demonstrates either better or comparable performance w.r.t. BERT-based models.

Chinese semantic matching is a fundamental task in natural language processing, which is critical and yet challenging for a series of downstream tasks. Although recent work on text representation learning has shown its potential in improving the performance on semantic matching, relatively limited work has been done on exploring the relevant interactive information between two granularity of Chinese text, i.e., character and word. Existing methods usually focus on capturing the interactive features from single granularity, which lead to inefficient text representation. Also, they typically fail to consider the fusion of features from different granularity. As a result, they only achieve limited performance improvement. This paper proposes a novel Chinese semantic matching model based on multi-granularity alignment and feature fusion (MAFFo). To be specific, we first encode the texts from different granularity, which are further handled with soft-alignment attention mechanism to extract relevant interactive information between texts on different granularity. In addition, we devise a feature fusion structure to merge the features from different granularity to generate an ideal representation for the pair of input text sequences, followed by a sigmoid function to judge the semantic matching degree. Extensive experiments on the publicly available dataset BQ demonstrate that our model can effectively improve the performance of semantic matching task and achieve comparable performance with BERT-based methods.

Summary The precise named entity recognition (NER) is a key component in Chinese clinical natural language processing. Although clinical NER systems have attracted widespread attention and been studied for decades, the latest NER research usually relies on a shallow text representation with one‐layer neural encoding, which fails to capture deep features and limits its performance improvement. To capture more features and encode the clinical text efficiently, we propose a deep stacked neural network for Chinese clinical NER. The neural network stacks two bidirectional long‐short term memory and gated recurrent unit layers to encode the text twice, followed by a conditional random fields (CRF) layer to recognize named entities in Chinese clinical text. Extensive empirical results on three real‐world datasets demonstrate that the proposed method significantly outperforms six state‐of‐the‐art NER methods. Especially compared with the conventional CRF model, our method has at least 3.75% F1‐score improvement on these public datasets.

The development of cognitive robotics brings an attractive scenario where humans and robots cooperate to accomplish specific tasks. To facilitate this scenario, cognitive robots are expected to have the ability to interact with humans with natural language, which depends on natural language understanding ( NLU ) technologies. As one core task in NLU, sentence semantic matching ( SSM ) has widely existed in various interaction scenarios. Recently, deep learning–based methods for SSM have become predominant due to their outstanding performance. However, each sentence consists of a sequence of words, and it is usually viewed as one-dimensional ( 1D ) text, leading to the existing available neural models being restricted into 1D sequential networks. A few researches attempt to explore the potential of 2D or 3D neural models in text representation. However, it is hard for their works to capture the complex features in texts, and thus the achieved performance improvement is quite limited. To tackle this challenge, we devise a novel 3D CNN-based SSM ( 3DSSM ) method for human–robot language interaction. Specifically, first, a specific architecture called feature cube network is designed to transform a 1D sentence into a multi-dimensional representation named as semantic feature cube. Then, a 3D CNN module is employed to learn a semantic representation for the semantic feature cube by capturing both the local features embedded in word representations and the sequential information among successive words in a sentence. Given a pair of sentences, their representations are concatenated together to feed into another 3D CNN to capture the interactive features between them to generate the final matching representation. Finally, the semantic matching degree is judged with the sigmoid function by taking the learned matching representation as the input. Extensive experiments on two real-world datasets demonstrate that 3DSSM is able to achieve comparable or even better performance over the state-of-the-art competing methods.

Sentence intention matching is vital for natural language understanding.Especially for Chinese sentence intention matching task, due to the ambiguity of Chinese words, semantic missing or semantic confusion are more likely to occur in the encoding process.Although the existing methods have enriched text representation through pre-trained word embedding to solve this problem, due to the particularity of Chinese text, different granularities of pre-trained word embedding will affect the semantic description of a piece of text.In this paper, we propose an effective approach that combines charactergranularity and word-granularity features to perform sentence intention matching, and we utilize soft alignment attention to enhance the local information of sentences on the corresponding levels.The proposed method can capture sentence feature information from multiple perspectives and correlation information between different levels of sentences.By evaluating on BQ and LCQMC datasets, our model has achieved remarkable results, and demonstrates better or comparable performance with BERT-based models.