Metaphor, as a common type of linguistic expression, helps people intuitively understand complex concepts in communication, writing, and cognition. Metaphor components, including source-domain words and target-domain words, are critical elements for metaphor identification and interpretation. This article focuses on metaphor components and proposes a metaphor components identification framework employing F eedback-enhanced F eature-driven I n- C ontext L earning (FF-ICL) based on the large language model (LLM). Specifically, in-context learning and feedback mechanisms inspired by human learning are integrated. Firstly, a machine feedback mechanism is designed to perform prior predictions on training samples, constructing a candidate demonstration pool enriched with prediction results and feedback information. Secondly, a multi-head graph attention network (GAT) is introduced to capture the linguistic and structural information embedded in metaphorical expressions, producing feature-rich representations and establishing a vector repository. Based on the repository, the framework retrieves demonstrations most relevant to the input query across different feature dimensions, incorporating in-context prompts to effectively fine-tune the LLM. Experiments and analyses on public datasets demonstrate the superiority of FF-ICL. Furthermore, the metaphor concept mapping experiment validates the crucial role of metaphor components in downstream computational metaphor tasks. Relevant data and codes are available at https://github.com/WXLJZ/FF-ICL .

Emotion recognition in conversations (ERC) has garnered significant attention from the research community. However, due to the complexity of visual scenes and dialogue contextual dependencies in conversations, previous ERC methods fail to handle emotional cues from both visual sources and discourse structures. Furthermore, existing state-of-the-art ERC models are trained and tested separately on each single ERC dataset, not verifying their effectiveness across multiple datasets simultaneously. To address these challenges, this paper proposes an innovative framework for ERC, called Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning (DialogueMMT). More concretely, a novel video-language connector is applied within the large vision-language model for capturing video features effectively. Additionally, we utilize multi-task instruction tuning with a unified ERC dataset to enhance the model’s understanding of multi-modal dialogue scenes and employ a chain-of-thought strategy to improve emotion classification performance. Extensive experimental results on three benchmark ERC datasets indicate that the proposed DialogueMMT framework consistently outperforms existing state-of-the-art approaches in terms of overall performance.

Entities are important to understanding literary works, which emphasize characters, plots and environment. The research on entity recognition, especially nested entity recognition in the literary domain is still insufficient partly due to insufficient annotated data. To address this issue, we construct the first Genre-oriented Corpus for Entity Recognition in Chinese Web Novels, namely GenWebNovel, comprising 400 chapters totaling 1,214,283 tokens under two genres, XuanHuan (Eastern Fantasy) and History. Based on the corpus, we analyze the distribution of different types of entities, including person, location, and organization. We also compare the nesting patterns of nested entities between GenWebNovel and the English corpus LitBank. Even though both belong to the literary domain, entities in different genres share few overlaps, making genre adaptation of NER (Named Entity Recognition) a hard problem. We propose a novel method that utilizes a pre-trained language model as an In-context learning example retriever to boost the performance of large language models. Our experiments show that this approach significantly enhances entity recognition, matching state-of-the-art (SOTA) models without requiring additional training data. Our code, dataset, and model are available at https://github.com/hjzhao73/GenWebNovel.

In recent years, fine-grained sentiment analysis in finance has gained significant attention, but the scarcity of entity-level datasets remains a key challenge. To address this, we have constructed the largest English and Chinese financial entity-level sentiment analysis datasets to date. Building on this foundation, we propose a novel two-stage sentiment analysis approach called Self-aware In-context Learning Correction (SILC). The first stage involves fine-tuning a base large language model to generate pseudo-labeled data specific to our task. In the second stage, we train a correction model using a GNN-based example retriever, which is informed by the pseudo-labeled data. This two-stage strategy has allowed us to achieve state-of-the-art performance on the newly constructed datasets, advancing the field of financial sentiment analysis. In a case study, we demonstrate the enhanced practical utility of our data and methods in monitoring the cryptocurrency market. Our datasets and code are available at https://github.com/NLP-Bin/SILC-EFSA.

This paper focuses on Dialogue Aspect-based Sentiment Quadruple (DiaASQ) analysis, aiming to extract structured quadruples from multiturn conversations.Applying Large Language Models (LLMs) for this specific task presents two primary challenges: the accurate extraction of multiple elements and the understanding of complex dialogue reply structure.To tackle these issues, we propose a novel LLMbased multi-task approach, named Task-aware Contrastive Mixture of Experts (TaCoMoE), to tackle the DiaASQ task by integrating expertlevel contrastive loss within task-oriented mixture of experts layer.TaCoMoE minimizes the distance between the representations of the same expert in the semantic space while maximizing the distance between the representations of different experts to efficiently learn representations of different task samples.Additionally, we design a Graph-Centric Dialogue Structuring strategy for representing dialogue reply structure and perform non-opinion utterances detection to enhance the performance of quadruple extraction.Extensive experiments are conducted on the DiaASQ dataset, demonstrating that our method significantly outperforms existing parameter-efficient fine-tuning techniques in terms of both accuracy and computational efficiency.The code is available at https://github.com/he2720/TaCoMoE.

Metasurface can manipulate electromagnetic (EM) waves flexibly, which provides the basis for functional integration. Recently, the efficient machine‐learning‐assisted methods have attracted intensive attentions in multifunctional metasurfaces design. However, the conventional machine‐learning‐assisted metasurfaces design is to fit the internal relationship in the form of black box, which ignores the underlying physical logic, resulting in the increased complexity of machine learning architecture with the parameters increasing. In order to adapt to the multiparameter optimization in multifunctional metasurfaces design, we propose a multiplexing neural network (MNN) based on decoupling at the physical layer to simplify both the structural parameters and the network architecture. The four interacting parameters are simplified into four independently regulated parameters so that the facile design of four functions can be realized only by multiplexing a simple neural network. For verification, four functions of scattering, anomalous reflection, focusing, and hologram are integrated in the same metasurface aperture by MNN. Performances of the metasurface are fully demonstrated by simulation and measurement. Importantly, this work paves the way for the bidirectional simplification of machine learning and metasurface design via physical inspiration, which provides an integrated design method of multifunctional metasurfaces and can be potentially applied to satellite communications and other fields.

Recent advances in Large Language Models (LLMs) have achieved remarkable breakthroughs in understanding and responding to user intents. However, their performance lag behind general use cases in some expertise domains, such as Chinese medicine. Existing efforts to incorporate Chinese medicine into LLMs rely on Supervised Fine-Tuning (SFT) with single-turn and distilled dialogue data. These models lack the ability for doctor-like proactive inquiry and multi-turn comprehension and cannot align responses with experts' intentions. In this work, we introduce Zhongjing, the first Chinese medical LLaMA-based LLM that implements an entire training pipeline from continuous pre-training, SFT, to Reinforcement Learning from Human Feedback (RLHF). Additionally, we construct a Chinese multi-turn medical dialogue dataset of 70,000 authentic doctor-patient dialogues, CMtMedQA, which significantly enhances the model's capability for complex dialogue and proactive inquiry initiation. We also define a refined annotation rule and evaluation criteria given the unique characteristics of the biomedical domain. Extensive experimental results show that Zhongjing outperforms baselines in various capacities and matches the performance of ChatGPT in some abilities, despite the 100x parameters. Ablation studies also demonstrate the contributions of each component: pre-training enhances medical knowledge, and RLHF further improves instruction-following ability and safety. Our code, datasets, and models are available at https://github.com/SupritYoung/Zhongjing.

In medical information extraction, medical Named Entity Recognition (NER) is indispensable, playing a crucial role in developing medical knowledge graphs, enhancing medical question-answering systems, and analyzing electronic medical records. The challenge in medical NER arises from the complex nested structures and sophisticated medical terminologies, distinguishing it from its counterparts in traditional domains. In response to these complexities, we propose a medical NER model based on Machine Reading Comprehension (MRC), which uses a task-adaptive pre-training strategy to improve the model’s capability in the medical field. Meanwhile, our model introduces multiple word-pair embeddings and multi-granularity dilated convolution to enhance the model’s representation ability and uses a combined predictor of Biaffine and MLP to improve the model’s recognition performance. Experimental evaluations conducted on the CMeEE, a benchmark for Chinese nested medical NER, demonstrate that our proposed model outperforms the compared state-of-the-art (SOTA) models.

Multi-domain aspect-based sentiment analysis (ABSA) seeks to capture fine-grained sentiment across diverse domains. While existing research narrowly focuses on single-domain applications constrained by methodological limitations and data scarcity, the reality is that sentiment naturally traverses multiple domains. Although large language models (LLMs) offer a promising solution for ABSA, it is difficult to integrate effectively with established techniques, including graph-based models and linguistics, because modifying their internal architecture is not easy. To alleviate this problem, we propose a novel framework, Feature-aware In-context Learning for Multi-domain ABSA (FaiMA). The core insight of FaiMA is to utilize in-context learning (ICL) as a feature-aware mechanism that facilitates adaptive learning in multi-domain ABSA tasks. Specifically, we employ a multi-head graph attention network as a text encoder optimized by heuristic rules for linguistic, domain, and sentiment features. Through contrastive learning, we optimize sentence representations by focusing on these diverse features. Additionally, we construct an efficient indexing mechanism, allowing FaiMA to stably retrieve highly relevant examples across multiple dimensions for any given input. To evaluate the efficacy of FaiMA, we build the first multi-domain ABSA benchmark dataset. Extensive experimental results demonstrate that FaiMA achieves significant performance improvements in multiple domains compared to baselines, increasing F1 by 2.07% on average. Source code and data sets are available at https://github.com/SupritYoung/FaiMA.

The Biomedical Entity Normalization (BEN) task aims to align raw, unstructured medical entities to standard entities, thus promoting data coherence and facilitating better downstream medical applications. Recently, prompt learning methods have shown promising results in the natural language processing field. However, existing research falls short in tackling the more complex Chinese BEN task, especially in the few-shot scenario with limited medical data, and the vast potential of the external medical knowledge base has not yet been fully exploited. To address these challenges, this article proposes a novel Knowledge-injected Prompt Learning (PL-Knowledge) method. Specifically, the approach consists of five stages: candidate entity matching, knowledge extraction, knowledge encoding, knowledge injection, and prediction output. By effectively encoding the knowledge items contained in medical entities and incorporating them into tailor-made knowledge-injected templates, the additional knowledge enhances the model’s ability to capture latent relationships between medical entities, thus achieving a better match with the standard entities. Comprehensive experiments are conducted on a benchmark dataset in both few-shot and full-scale settings. This method outperforms existing baselines, with an average accuracy improvement of 12.96 percentage points in few-shot and 0.94 percentage points in full-data cases, showcasing its excellence in the BEN task.

Aspect Sentiment Triplet Extraction (ASTE) aims to extract sentiment triplets from texts. Previous studies attempted to use an unsupervised perturbed masking technique to derive syntax trees from pre-trained language models (PLMs) to extract aspect sentiment simply. However, existing methods neglect further exploration of the technique for more complex tasks like ASTE. In this paper, we propose a novel Edge-enhanced Sentiment Graph Attention Network model (ES-GAT), which transforms the impact matrix generated by the technique into a new linguistic feature, and uses a novel effective fusion strategy to incorporate multiple features, which can better capture the implicit connections among sentiment elements. In the graph attention module, we simultaneously consider edge and node attention weight calculations and updates to solve the edge-sensitive end to end ASTE task. Experiments show that our model outperforms the strong baselines. The F1 scores are improved by 2.52% and 1.56% on average on the two versions of the benchmark datasets.11Code and datasets are available at https://github.com/SupritYoung/ESGAT

Emotion recognition in conversation is important for an empathetic dialogue system to understand the user’s emotion and then generate appropriate emotional responses. However, most previous researches focus on modeling conversational contexts primarily based on the textual modality or simply utilizing multimodal information through feature concatenation. In order to exploit multimodal information and contextual information more effectively, we propose a multimodal directed acyclic graph (MMDAG) network by injecting information flows inside modality and across modalities into the DAG architecture. Experiments on IEMOCAP and MELD show that our model outperforms other state-of-the-art models. Comparative studies validate the effectiveness of the proposed modality fusion method.

In the past few years, it has become increasingly popular to analyze the information obtained to develop services by conducting a decentralized survey of private data for specific populations. Privacy security requirements for data providers force operators to implement reasonable privacy protections. But increasing the investment in privacy protection will also lead to a decline in operator revenue. In this case, operators need to ensure the privacy and security requirements of users while ensuring the sustainability of customized services. To this end, We study the relationship between collecting data quality and operator strategy, quantifying the price of private data, and building a model to maximize operator profitability. Specifically, closed-form solutions for best privacy data prices and subscription fees are designed to maximize the gross profit of service providers. Also includes the collection of data quality factors to ensure that the user perceived quality of service can be guaranteed to a certain extent. Finally, we explored the relationship between spending, subscription fees, and maximum gross profit of carriers during the data collection phase, based on the distribution of different user groups' privacy attitudes. In particular, we also explored the relationship between adding additional noise and collecting data utility in a decentralized privacy protection scenario. The simulation results show that compared with the existing methods, the algorithm can maximize the collected data quality while ensuring the provider's privacy security requirements. In addition, we demonstrate the benefits of our dynamic pricing approach and its applicability to other private data pricing algorithms.

Text normalization is an important component in text-to-speech system and the difficulty in text normalization is to disambiguate the non-standard words (NSWs). This paper develops a taxonomy of NSWs on the basis of a large scale Chinese corpus, and proposes a two-stage NSWs disambiguation strategy, finite state automata (FSA) for initial classification and maximum entropy (ME) classifiers for subclass disambiguation. Based on the above NSWs taxonomy, the two-stage approach achieves an F-score of 98.53% in open test, 5.23% higher than that of FSA based approach. Experiments show that the NSWs taxonomy ensures FSA a high baseline performance and ME classifiers make considerable improvement, and the two-stage approach adapts well to new domains.