Sequential recommendation (SR) aims to predict a user's next item preference by modeling historical interaction sequences. Recent advances often integrate frequency-domain modules to compensate for self-attention's low-pass nature by restoring the high-frequency signals critical for personalized recommendations. Nevertheless, existing frequency-aware solutions process each session in isolation and optimize exclusively with time-domain objectives. Consequently, they overlook cross-session spectral dependencies and fail to enforce alignment between predicted and actual spectral signatures, leaving valuable frequency information under-exploited. To this end, we propose FreqRec, a Frequency-Enhanced Dual-Path Network for sequential Recommendation that jointly captures inter-session and intra-session behaviors via a learnable Frequency-domain Multi-layer Perceptron. Moreover, FreqRec is optimized under a composite objective that combines cross entropy with a frequency-domain consistency loss, explicitly aligning predicted and true spectral signatures. Extensive experiments on three benchmarks show that FreqRec surpasses strong baselines and remains robust under data sparsity and noisy-log conditions.

Multivariate time series forecasting (MTSF) aims to predict future values based on historical observations. Recently, Fuzzy Cognitive Maps (FCM) have emerged as a promising and interpretable approach for MTSF. However, existing FCM-based models suffer from two main limitations. First, their feature extraction mechanisms fail to effectively represent raw time series data, limiting the ability to capture complex spatiotemporal dependencies. Second, the single-variable composite modeling strategy adopted by high-order FCMs (HFCM) neglects holistic inter-variable relationships across time, leading to inefficiencies and a linear increase in model parameters. To overcome these challenges, we propose a novel framework—Context-Aware Enhanced FCM (CAE-FCM)—for interpretable MTSF. To address the first limitation, CAE-FCM introduces two complementary feature extraction modules: the Adaptive Graph Convolution (AGC) module, which captures spatial dependencies through neighborhood-aware information aggregation, and the Global-Local Context-Aware Mamba (GLCAM) module, which models temporal dependencies via a state space model (SSM) that learns global and local temporal dynamics. For second limitation, CAE-FCM integrates the extracted spatial and temporal features into unified high-dimensional representations for FCM nodes, enabling efficient and expressive modeling of complex spatiotemporal interactions. Extensive experiments on five benchmark datasets demonstrate that CAE-FCM achieves state-of-the-art performance, significantly outperforming HFCM-based baselines in both forecasting accuracy and computational efficiency.

Fusing side information in session-based recommendation is crucial for improving the performance of next-item prediction by providing additional context. Recent methods optimize attention weights by combining item and side information embeddings. However, semantic heterogeneity between item IDs and side information introduces computational noise in attention calculation, leading to inconsistencies in user interest modeling and reducing the accuracy of candidate item scores. These methods also often fail to leverage session-based re-interaction patterns, limiting improvements in score prediction during the decoding phase. To address these challenges, we propose ScoreNet, a consistency-driven framework with multi-side information fusion for session-based recommendation. ScoreNet explicitly models users' persistent preferences, generating consistent decoding scores for candidate items within a unified framework. It incorporates a multi-path re-engagement network to capture re-interaction behavior patterns in a semantic-agnostic manner, enhancing side information fusion while avoiding semantic interference. Additionally, a position-enhanced consistent scoring network redistributes attention scores within sessions, improving prediction accuracy, especially for items with limited interactions. Extensive experiments on three real-world datasets demonstrate that ScoreNet outperforms state-of-the-art models.

Multimodal emotion recognition (MER) aims to identify emotional states by integrating and analyzing information from multiple modalities. However, inherent modality heterogeneity and inconsistencies in emotional cues remain key challenges that hinder performance. To address these issues, we propose a Decoupled Representations with Knowledge Fusion (DRKF) method for MER. DRKF consists of two main modules: an Optimized Representation Learning (ORL) Module and a Knowledge Fusion (KF) Module. ORL employs a contrastive mutual information estimation method with progressive modality augmentation to decouple task-relevant shared representations and modality-specific features while mitigating modality heterogeneity. KF includes a lightweight self-attention-based Fusion Encoder (FE) that identifies the dominant modality and integrates emotional information from other modalities to enhance the fused representation. To handle potential errors from incorrect dominant modality selection under emotionally inconsistent conditions, we introduce an Emotion Discrimination Submodule (ED), which enforces the fused representation to retain discriminative cues of emotional inconsistency. This ensures that even if the FE selects an inappropriate dominant modality, the Emotion Classification Submodule (EC) can still make accurate predictions by leveraging preserved inconsistency information. Experiments show that DRKF achieves state-of-the-art (SOTA) performance on IEMOCAP, MELD, and M3ED. The source code is publicly available at https://github.com/PANPANKK/DRKF.

Few-shot Relation Extraction (FSRE) aims to extract relational facts from a sparse set of labeled corpora. Recent studies have shown promising results in FSRE by employing Pre-trained Language Models (PLMs) within the framework of supervised contrastive learning, which considers both instances and label facts. However, how to effectively harness massive instance-label pairs to encompass the learned representation with semantic richness in this learning paradigm is not fully explored. To address this gap, we introduce a novel synergistic anchored contrastive pre-training framework. This framework is motivated by the insight that the diverse viewpoints conveyed through instance-label pairs capture incomplete yet complementary intrinsic textual semantics. Specifically, our framework involves a symmetrical contrastive objective that encompasses both sentence-anchored and label-anchored contrastive losses. By combining these two losses, the model establishes a robust and uniform representation space. This space effectively captures the reciprocal alignment of feature distributions among instances and relational facts, simultaneously enhancing the maximization of mutual information across diverse perspectives within the same relation. Experimental results demonstrate that our framework achieves significant performance enhancements compared to baseline models in downstream FSRE tasks. Furthermore, our approach exhibits superior adaptability to handle the challenges of domain shift and zero-shot relation extraction. Our code is available online at https://github.com/AONE-NLP/FSRE-SaCon.

Yuxiang Cai, Qiao Liu, Yanglei Gan, Run Lin, Changlin Li, Xueyi Liu, Da Luo, JiayeYang JiayeYang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Joint entity-relation extraction remains a challenging task in information retrieval, given the intrinsic difficulty in modelling the interdependence between named entity recognition (NER) and relation extraction (RE) sub-tasks. Most existing joint extraction models encode entity and relation features in a sequential or parallel manner, allowing for limited one-way interaction. However, it is not yet clear how to capture the interdependence between these two sub-tasks in a synergistic and mutually reinforcing fashion. With this in mind, we propose a novel approach for joint entity-relation extraction, named Synergetic Interaction Network (SINET) which utilizes a cross-task attention mechanism to effectively leverage contextual associations between NER and RE. Specifically, we construct two sets of distinct token representations for NER and RE sub-tasks respectively. Then, both sets of unique representation interact with one another via a cross-task attention mechanism, which exploits associated contextual information produced by concerted efforts of both NER and RE. Experiments on three benchmark datasets demonstrate that the proposed model achieves significantly better performance in joint entity-relation extraction. Moreover, extended analysis validates that the proposed mechanism can indeed leverage the semantic information produced by NER and RE sub-tasks to boost one another in a complementary way. The source code is available to the public online.

ISP (Image Signal Processor) serves as a pipeline converting unprocessed raw images to sRGB images, positioned before nearly all visual tasks. Due to the varying spectral sensitivities of cameras, raw images captured by different cameras exist in different color spaces, making it challenging to deploy ISP across cameras with consistent performance. To address this challenge, it is intuitively to incorporate a raw-to-raw mapping (mapping raw images across camera color spaces) module into the ISP. However, the lack of paired data (i.e., images of the same scene captured by different cameras) makes it difficult to train a raw-to-raw model using supervised learning methods. In this paper, we aim to achieve ISP generalization by proposing the first unsupervised raw-to-raw model. To be specific, we propose a CSTPP (Color Space Transformation Parameters Predictor) module to predict the space transformation parameters in a patch-wise manner, which can accurately perform color space transformation and flexibly manage complex lighting conditions. Additionally, we design a CycleGAN-style training framework to realize unsupervised learning, overcoming the deficiency of paired data. Our proposed unsupervised model achieved performance comparable to that of the state-of-the-art semi-supervised method in raw-to-raw task. Furthermore, to assess its ability to generalize the ISP model across different cameras, we for the first formulated cross-camera ISP task and demonstrated the performance of our method through extensive experiments. The codes are released at https://github.com/ydxxxx/Unsupervised-Raw-to-raw-Mapping.

Aspect-based sentiment classification is a crucial problem in fine-grained sentiment analysis, which aims to predict the sentiment polarity of the given aspect according to its context. Previous works have made remarkable progress in leveraging attention mechanism to extract opinion words for different aspects. However, a persistent challenge is the effective management of semantic mismatches, which stem from attention mechanisms that fall short in adequately aligning opinions words with their corresponding aspect in multi-aspect sentences. To address this issue, we propose a novel Aspect-oriented Opinion Alignment Network (AOAN) to capture the contextual association between opinion words and the corresponding aspect. Specifically, we first introduce a neighboring span enhanced module which highlights various compositions of neighboring words and given aspects. In addition, we design a multi-perspective attention mechanism that align relevant opinion information with respect to the given aspect. Extensive experiments on three benchmark datasets demonstrate that our model achieves state-of-the-art results. The source code is available at https://github.com/AONE-NLP/ABSA-AOAN.

Speech enhancement aims to recover clean speech from complex noise backgrounds. This paper proposes a novel information processing module dubbed dynamic scene perception module (DSPM) that can help existing systems to accommodate various complex scenarios. The inspiration of DSPM is based on the observation that different regions of the noisy spectrum in different scenarios have different enhancing requirements. Concretely, DSPM consists of two parts, one for dynamic scene estimation, and the other for adaptive region perception. In particular, the scene estimator utilizes a spectrum-energy-based attention mechanism to obtain the coefficients of each convolution kernel. Then, at each position’ the region perceptron chooses the corresponding kernels by considering the requirements of the current region (preserve vocals or suppress noise). Systematic evaluations on the TIMIT corpus and Voice Bank + DEMAND demonstrate the effectiveness of our method. Compared with the existing systems, our proposed method achieved better performance under various SNR conditions and complex noise scenarios.

Speech enhancement aims to restore clean speech from noisy environments. In recent years, skip connections have shown great promise in improving speech enhancement performance. Although directly transmitting low-level information is helpful for reconstructing the spectrum, the noise components negatively impact denoising results. In this letter, we propose IDANet, an end-to-end framework that incorporates an information distillation and aggregation unit to store fine-grained features and filter out noisy components through continuous distillation and recalibration. In addition, we design a novel decoding block equipped with deformable convolution and dynamic attention mechanism to further improve the capability of the reconstruction unit. Experimental results conducted on TIMIT corpus demonstrate that the proposed IDANet is efficient yet effective, e.g., the parameters of our model against the state-of-the-art model are 0.68M vs. 1.23M, and the performance boost on STOI and PESQ is 0.81% and 3.73%.

The redundant convolutional encoder-decoder network has proven useful in speech enhancement tasks. It can capture localized time-frequency details of speech signals through both the fully convolutional network structure and feature selection capability resulting from the encoder-decoder mechanism. However, it does not explicitly consider the signal filtering mechanism, which we regard as important for speech enhancement models. In this study, we introduce an attention mechanism into the convolutional encoderdecoder model. This mechanism adaptively filters channelwise feature responses by explicitly modeling attentions (on speech versus noise signals) between channels. Experimental results show that the proposed attention model is effective in capturing speech signals from background noise, and performs especially better in unseen noise conditions compared to other state-of-the-art models.

Hydropower is the largest renewable energy source for electricity generation in the world, with numerous benefits in terms of: environment protection (near-zero air pollution and climate impact), cost-effectiveness (long-term use, without significant impacts of market fluctuation), and reliability (quickly respond to surge in demand). However, the effectiveness of hydropower plants is affected by multiple factors such as reservoir capacity, rainfall, temperature and fluctuating electricity demand, and particularly their complicated relationships, which make the prediction/recommendation of station operational output a difficult challenge. In this paper, we present DeepHydro, a novel stochastic method for modeling multivariate time series (e.g., water inflow/outflow and temperature) and forecasting power generation of hydropower stations. DeepHydro captures temporal dependencies in co-evolving time series with a new conditioned latent recurrent neural networks, which not only considers the hidden states of observations but also preserves the uncertainty of latent variables. We introduce a generative network parameterized on a continuous normalizing flow to approximate the complex posterior distribution of multivariate time series data, and further use neural ordinary differential equations to estimate the continuous-time dynamics of the latent variables constituting the observable data. This allows our model to deal with the discrete observations in the context of continuous dynamic systems, while being robust to the noise. We conduct extensive experiments on real-world datasets from a large power generation company consisting of cascade hydropower stations. The experimental results demonstrate that the proposed method can effectively predict the power production and significantly outperform the possible candidate baseline approaches.

Review text has been widely studied in traditional tasks such as sentiment analysis and aspect extraction. However, to date, no work is towards the abstractive review summarization that is essential for business organizations and individual consumers to make informed decisions. This work takes the lead to study the aspect/sentiment-aware abstractive review summarization by exploring multi-factor attentions. Specifically, we propose an interactive attention mechanism to interactively learns the representations of context words, sentiment words and aspect words within the reviews, acted as an encoder. The learned sentiment and aspect representations are incorporated into the decoder to generate aspect/sentiment-aware review summaries via an attention fusion network. In addition, the abstractive summarizer is jointly trained with the text categorization task, which helps learn a category-specific text encoder, locating salient aspect information and exploring the variations of style and wording of content with respect to different text categories. The experimental results on a real-life dataset demonstrate that our model achieves impressive results compared to other strong competitors.

Predicting users' actions based on anonymous sessions is a challenging problem in web-based behavioral modeling research, mainly due to the uncertainty of user behavior and the limited information. Recent advances in recurrent neural networks have led to promising approaches to solving this problem, with long short-term memory model proving effective in capturing users' general interests from previous clicks. However, none of the existing approaches explicitly take the effects of users' current actions on their next moves into account. In this study, we argue that a long-term memory model may be insufficient for modeling long sessions that usually contain user interests drift caused by unintended clicks. A novel short-term attention/memory priority model is proposed as a remedy, which is capable of capturing users' general interests from the long-term memory of a session context, whilst taking into account users' current interests from the short-term memory of the last-clicks. The validity and efficacy of the proposed attention mechanism is extensively evaluated on three benchmark data sets from the RecSys Challenge 2015 and CIKM Cup 2016. The numerical results show that our model achieves state-of-the-art performance in all the tests.

Aspect based sentiment classification is a crucial task for sentiment analysis. Recent advances in neural attention models demonstrate that they can be helpful in aspect based sentiment classification tasks, which can help identify the focus words in human. However, according to our empirical study, prevalent content attention mechanisms proposed for aspect based sentiment classification mostly focus on identifying the sentiment words or shifters, without considering the relevance of such words with respect to the given aspects in the sentence. Therefore, they are usually insufficient for dealing with multi-aspect sentences and the syntactically complex sentence structures. To solve this problem, we propose a novel content attention based aspect based sentiment classification model, with two attention enhancing mechanisms: sentence-level content attention mechanism is capable of capturing the important information about given aspects from a global perspective, whiles the context attention mechanism is responsible for simultaneously taking the order of the words and their correlations into account, by embedding them into a series of customized memories. Experimental results demonstrate that our model outperforms the state-of-the-art, in which the proposed mechanisms play a key role.

Relational inference is a crucial technique for knowledge base population. The central problem in the study of relational inference is to infer unknown relations between entities from the facts given in the knowledge bases. Two popular models have been put forth recently to solve this problem, which are the latent factor models and the random-walk models, respectively. However, each of them has their pros and cons, depending on their computational efficiency and inference accuracy. In this paper, we propose a hierarchical random-walk inference algorithm for relational learning in large scale graph-structured knowledge bases, which not only maintains the computational simplicity of the random-walk models, but also provides better inference accuracy than related works. The improvements come from two basic assumptions we proposed in this paper. Firstly, we assume that although a relation between two entities is syntactically directional, the information conveyed by this relation is equally shared between the connected entities, thus all of the relations are semantically bidirectional. Secondly, we assume that the topology structures of the relation-specific subgraphs in knowledge bases can be exploited to improve the performance of the random-walk based relational inference algorithms. The proposed algorithm and ideas are validated with numerical results on experimental data sampled from practical knowledge bases, and the results are compared to state-of-the-art approaches.