While large language models (LLMs) have made significant progress in expanding their context windows, they still face great challenges in effectively organizing and utilizing long-term memory to maintain conversation consistency and coherence. Summarizing historical conversations has achieved remarkable performance, which, however, loses conversational trajectory and association, making it difficult to precisely combine memories from different sessions in response to current queries. To address this, we propose the Dynamic Memory Forest (DMF), a novel Consolidation-then-Growth framework for long-term open-domain conversation, which simulates the consolidation and growth processes of human memory by dynamically organizing long-term conversation histories into a memory forest of memory trees. To be specific, inspired by the principles of synaptic consolidation and plasticity from Cognitive Science, we first consolidate each session into memory units that preserve thematic coherence ("Consolidation"). Then, we first structure these units into memory trees and then grow the forest by dynamically connecting them through an evolutionary grafting mechanism, called Group Relative Voting Optimization, which mimics synaptic connection to decide whether a new memory tree should be grafted onto the existing forest or grow independently ("Growth"). For retrieval, we design an Entropy-Driven Memory Walk, constructing a logically coherent memory path via a navigation policy that prioritizes exploring high-entropy nodes. Experiments on three long-term conversation datasets show that our DMF significantly outperforms baselines in enhancing response generation for LLMs.

Large language model driven multi-agent social simulation frameworks enable realistic modeling of complex societal dynamics but incur substantial computational overhead due to dense agent participation and extensive interaction costs. To address this limitation, we propose SocialDropout, a reinforcement learning–based agent selection strategy within the AgentSociety framework, inspired by the AgentDropout paradigm, which dynamically identifies and samples informative agent subsets for each simulation round. Each agent is assigned an adaptive importance weight optimized to jointly minimize agent sparsity and computational cost measured by LLM calls, token consumption, and execution time—while preserving social interaction intensity within the environment. Extensive performance evaluation demonstrates that the proposed method significantly improves simulation efficiency and scalability. Moreover, ablation studies verify that high-level behavioral realism and outcome consistency are largely maintained despite substantial agent reduction. Our approach offers a practical and general optimization mechanism for large-scale LLM-based multi-agent social simulations under constrained computational budgets.

Contextual meme understanding decodes implicit meaning from ambiguous visual metaphors and social context, which is crucial for online communication analysis. However, existing linear reasoning paradigms reductively cast this process as deterministic decoding, overlooking the fundamental reality that meme interpretation necessitates the dynamic alignment of multimodal cues. Lacking mechanisms to measure and correct misalignment, these static models inevitably allow initial perceptual failures to cascade into irreversible hallucinations. To address this, we propose Semantic Energy Entropy Descent (SEED), a framework that reformulates contextual meme understanding as an energy minimization problem within a discrete semantic space. Specifically, SEED constructs a Convergent Heterogeneous Thought Tree (CHTT) as the optimization workspace, where an Evaluator Agent quantifies the semantic inconsistency of hypotheses via a Semantic Energy Mechanism. By calculating a Discrete Semantic Gradient as structured feedback, the framework activates a Supplier Agent to retrieve knowledge and context evidence and a Reasoner Agent to refine explanations, thereby orchestrating Semantic Descent Dynamics that iteratively drive the reasoning trajectory to converge on a stable, low-entropy interpretation. Experimental results show that SEED consistently outperforms strong baselines on both classification and generation, reducing logical hallucinations and improving cultural grounding.

Recent advances in Large Language Models (LLMs) have shifted affective computing from direct label prediction to deliberative reasoning, with Reinforcement Learning (RL) emerging as a promising means of cultivating such capabilities. However, existing RL-based methods are largely confined to single-task settings, requiring separate training pipelines for different affective domains and limiting transfer across related problems. To address this limitation, we propose Unified Affective Reasoning (UAR), an in-context reinforcement learning framework for learning generalizable affective reasoning under a unified multi-task paradigm. UAR jointly optimizes multiple affective tasks and leverages in-context demonstrations to reconcile heterogeneous annotation schemas across datasets, thereby aligning disparate label spaces while preserving task-specific supervision. Experiments on 16 standard benchmarks across emotion recognition, aspect-based sentiment analysis, stance detection, and sarcasm detection show that UAR consistently improves the underlying base models and generalizes effectively to held-out out-of-domain tasks. These results demonstrate that in-context reinforcement learning provides an effective path toward unified and generalizable affective reasoning. Code is available at https://github.com/farisxiong/UAR.

The understanding and cognition of time are the basis for large language models to understand the world. Although large language models (LLMs) have demonstrated strong capabilities in multiple reasoning tasks, they still have significant deficiencies in temporal reasoning, mainly due to the diversity of temporal expressions and the lack of temporal logic reasoning capabilities. In this study, we propose a novel Temporal Chain of Thought framework(TempCoT) to improve the performance of LLM in temporal reasoning tasks through a three-stage reasoning strategy. First, TempCoT explicitly extracts time constraints to ensure the accuracy of time references during reasoning. Second, a semantic retrieval mechanism is introduced to dynamically obtain key temporal facts to enhance the integrity and reliability of information. Finally, an explicit temporal logic reasoning module is constructed based on point algebra to improve the consistency and interpretability of reasoning. Experimental results show that TempCoT significantly improves the temporal reasoning performance of five different LLMs and shows stronger robustness on complex temporal tasks.

Modality incompleteness is a critical yet underexplored challenge in multimodal sentiment analysis (MSA). Existing efforts, trained and evaluated under fixed missing rates, struggle to adapt to real-world scenarios with varying missing rates. To address this, we propose the Missing Modality Adaptation Framework (M2AF), leveraging model-agnostic meta-learning to enhance robustness against different levels of modality incompleteness. M2AF operates in two stages: meta-training and meta-testing. In the meta-training stage, a pre-trained MSA model, initially optimized for fixed missing rates, is further adapted to different levels of missing rates-low, moderate, and high. In the meta-testing stage, the model rapidly updates its parameters using minimal training data to handle target missing scenarios. Experiments on two popular datasets demonstrate that M2AF significantly improves the performance and generalization of various MSA models, ensuring more robust sentiment analysis in real-world settings with different modality incompleteness.

Conversational stance detection, which aims to identify stances within conversation threads, has become a research hotspot recently. As the number of dialogue turns increases and the conversation content becomes more complex, existing methods that simply incorporate conversational context are insufficient to effectively capture the nuanced information necessary for accurate stance detection. To address this issue, we introduce a Multi-agent Reasoning Graph Knowledge Distillation (MRGKD) framework, leveraging conversational reasoning among multiple Large Language Models (LLMs) into smaller language models. Specifically, we first construct a multi-agent reasoning graph to infer implicit logical relationships within the conversational history from the diverse perspectives of multiple LLMs. To fully leverage the in-context learning capabilities of LLMs, we design a reasoning knowledge editing mechanism that internalizes new information by aligning the output distribution of smaller language models with both the conversational history and the knowledge derived from the multi-agent reasoning graph. Additionally, we incorporate a contrastive loss to distinguish between correct and incorrect reasoning, alongside a stance detection loss, to fine-tune the smaller language models. This approach not only ensures the accurate acquisition of logical knowledge but also preserves the integrity of the conversational history. Experiments conducted on two public datasets demonstrate that our MRGKD significantly outperforms all baselines.

Recent research in Multimodal Emotion Recognition in Conversations (MERC) focuses on multimodal fusion and modeling speaker-sensitive context. In addition to contextual information, personality traits also affect emotional perception. However, current MERC methods solely consider the personality influence of speakers, neglecting speaker-addressee interaction patterns. Additionally, the bottleneck problem of Emotion Shift (ES), where consecutive utterances by the same speaker exhibit different emotions has been long neglected in MERC. Early ES research fails to distinguish diverse shift patterns and simply introduces whether shifts occur as knowledge into the MERC model without considering the complementary nature of the two tasks. Based on this, we propose a Persona-infused Cross-task Graph Network (PCGNet). It first models the speaker-addressee interactive relationships by the persona-infused refinement network. Then, it learns the auxiliary task of ES Detection and the main task of MERC using cross-task connections to capture correlations across two tasks. Finally, we introduce shift-aware contrastive learning to discern diverse shift patterns. Experimental results demonstrate that PCGNet outperforms state-of-the-art methods on two widely used datasets.

In this paper, we leverage in-context learning (ICL) paradigm to handle few-shot aspect-based sentiment analysis (ABSA). Previous works first rank candidate examples by some metrics and then independently retrieve examples similar to test samples. However, their effectiveness may be discounted because of two limitations: in-context example redundancy and example preference misalignment between retriever and LLM. To alleviate them, we propose a novel framework that sequentially retrieves in-context examples. It not only considers which example is useful for the test sample but also prevents its information from being duplicated by already retrieved examples. Subsequently, we exploit the rewards of LLMs on retrieved in-context examples to optimize parameters for bridging preference gaps. Experiments on four ABSA datasets show that our framework is significantly superior to previous works.

The goal of semi-supervised text classification (SSTC) is to train a model by exploring both a small number of labeled data and a large number of unlabeled data, such that the learned semi-supervised classifier performs better than the supervised classifier trained on solely the labeled samples. Pseudo-labeling is one of the most widely used SSTC techniques, which trains a teacher classifier with a small number of labeled examples to predict pseudo labels for the unlabeled data. The generated pseudo-labeled examples are then utilized to train a student classifier, such that the learned student classifier can outperform the teacher classifier. Nevertheless, the predicted pseudo labels may be inaccurate, making the performance of the student classifier degraded. The student classifier may perform even worse than the teacher classifier. To alleviate this issue, in this paper, we introduce a dual meta-learning ( DML ) technique for semi-supervised text classification, which improves the teacher and student classifiers simultaneously in an iterative manner. Specifically, we propose a meta-noise correction method to improve the student classifier by proposing a Noise Transition Matrix (NTM) with meta-learning to rectify the noisy pseudo labels. In addition, we devise a meta pseudo supervision method to improve the teacher classifier. Concretely, we exploit the feedback performance from the student classifier to further guide the teacher classifier to produce more accurate pseudo labels for the unlabeled data. In this way, both teacher and student classifiers can co-evolve in the iterative training process. Extensive experiments on four benchmark datasets highlight the effectiveness of our DML method against existing state-of-the-art methods for semi-supervised text classification. We release our code and data of this paper publicly at https://github.com/GRIT621/DML.

Intent detection plays an essential role in dialogue systems. This paper takes the lead to study open compound domain adaptation (OCDA) for intent detection, which brings the advantage of improved generalization to unseen domains. OCDA for intent detection is indeed a more realistic domain adaptation setting, which learns an intent classifier from labeled source domains and adapts it to unlabeled compound target domains containing different intent classes with the source domains. At inference time, we test the intent classifier in open domains that contain previously unseen intent classes. To this end, we propose an Adversarial Meta Prompt Tuning method (called AMPT) for open compound domain adaptive intent detection. Concretely, we propose a meta prompt tuning method, which utilizes language prompts to elicit rich knowledge from large-scale pre-trained language models (PLMs) and automatically finds better prompt initialization that facilitates fast adaptation via meta learning. Furthermore, we leverage a domain adversarial training technique to acquire domain-invariant representations of diverse domains. By taking advantage of the collaborative effect of meta learning, prompt tuning, and adversarial training, we can learn an intent classifier that can effectively generalize to unseen open domains. Experimental results on two benchmark datasets (i.e., HWU64 and CLINC) show that our model can learn substantially better-generalized representations for unseen domains compared with strong competitors.

Deep neural models have become mainstream in relation extraction (RE), yielding state-of-the-art performance. However, most existing neural models are prone to spurious correlations between input features and prediction labels, making the models suffer from low robustness and generalization.In this paper, we propose a spurious correlation reduction method for RE via feature decomposition and semantic augmentation (denoted as FDSA). First, we decompose the original sentence representation into class-related features and context-related features. To obtain better context-related features, we devise a contrastive learning method to pull together the context-related features of the anchor sentence and its augmented sentences, and push away the context-related features of different anchor sentences. In addition, we propose gradient-based semantic augmentation on context-related features in order to improve the robustness of the RE model. Experiments on four datasets show that our model outperforms the strong competitors.

Significant progress has been made by joint entity and relation extraction methods, which directly generate the relation triplets and mitigate the issue of overlapping relations. However, previous models generate the entity-relation triplets solely from input sentences. Such information is insufficient to support the modeling of interactive information between entities and relations. In this paper, we define the features that provide mutual supports for entity and relation detection but can only be accessed at training time as privileged features for relation extraction, and devise two teacher models to exploit privileged entity and relation features, respectively. Meanwhile, we propose a novel contrastive student-teacher learning framework for joint extraction of entities and relations (STER), where a student network is encouraged to amalgamate privileged knowledge from two expert teacher networks that additionally utilize the privileged features, based on contrastive learning. Experiment results on three benchmark datasets (i.e., ADE, SciERC and CoNLL04) demonstrate that STER has robust superiority over competitors and sets state-of-the-art. For reproducibility, we will release the data and source code once the paper is accepted.

Existing aspect-based/category sentiment analysis methods have shown great success in detecting sentiment polarity toward a given aspect in a sentence with supervised learning, where the training and inference stages share the same pre-defined set of aspects. However, in practice, the aspect categories are changing rather than keeping fixed over time. Dealing with unseen aspect categories is under-explored in existing methods. In this article, we formulate a new few-shot aspect category sentiment analysis (FSACSA) task, which aims to effectively predict the sentiment polarity of previously unseen aspect categories. To this end, we propose a novel Aspect-Focused Meta-Learning (AFML) framework that constructs aspect-aware and aspect-contrastive representations from external knowledge to match the target aspect with aspects in the training set. Concretely, we first construct two auxiliary contrastive sentences for a given sentence with the incorporation of external knowledge, enabling the learning of sentence representations with a better generalization. Then, we devise an aspect-focused induction network to leverage the contextual sentiment toward a given aspect to refine the label vectors. Furthermore, we employ the episode-based meta-learning algorithm to train the whole network, so as to learn to generalize to novel aspects. Extensive experiments on multiple real-life datasets show that our proposed AFML framework achieves the state-of-the-art results for the FSACSA task.

Existing methods usually identify causal relations between events at the mention-level, which takes each event mention pair as a separate input. As a result, they either suffer from conflicts among causal relations predicted separately or require a set of additional constraints to resolve such conflicts. We propose to study this task in a more realistic setting, where event-level causality identification can be made. The advantage is two folds: 1) with modeling different mentions of an event as a single unit, no more conflicts among predicted results, without any extra constraints; 2) with the use of diverse knowledge sources (e.g., co-occurrence and coreference relations), a rich graph-based event structure can be induced from the document for supporting event-level causal inference. Graph convolutional network is used to encode such structural information, which aims to capture the local and non-local dependencies among nodes. Results show that our model achieves the best performance under both mention- and event-level settings, outperforming a number of strong baselines by at least 2.8% on F1 score.

In this paper, we study the semi-supervised text classification (SSTC) by exploring both labeled and extra unlabeled data. One of the most popular SSTC techniques is pseudo-labeling which assigns pseudo labels for unlabeled data via a teacher classifier trained on labeled data. These pseudo labeled data is then applied to train a student classifier. However, when the pseudo labels are inaccurate, the student classifier will learn from inaccurate data and get even worse performance than the teacher. To mitigate this issue, we propose a simple yet efficient pseudo-labeling framework called Dual Pseudo Supervision (DPS), which exploits the feedback signal from the student to guide the teacher to generate better pseudo labels. In particular, we alternately update the student based on the pseudo labeled data annotated by the teacher and optimize the teacher based on the student's performance via meta learning. In addition, we also design a consistency regularization term to further improve the stability of the teacher. With the above two strategies, the learned reliable teacher can provide more accurate pseudo-labels to the student and thus improve the overall performance of text classification. We conduct extensive experiments on three benchmark datasets (i.e., AG News, Yelp and Yahoo) to verify the effectiveness of our DPS method. Experimental results show that our approach achieves substantially better performance than the strong competitors. For reproducibility, we will release our code and data of this paper publicly at https://github.com/GRIT621/DPS.

Zero-shot cross-lingual event argument extraction (EAE) is a challenging yet practical problem in Information Extraction. Most previous works heavily rely on external structured linguistic features, which are not easily accessible in real-world scenarios. This paper investigates a translation-based method to implicitly project annotations from the source language to the target language. With the use of translation-based parallel corpora, no additional linguistic features are required during training and inference. As a result, the proposed approach is more cost effective than previous works on zero-shot cross-lingual EAE. Moreover, our implicit annotation projection approach introduces less noises and hence is more effective and robust than explicit ones. Experimental results show that our model achieves the best performance, outperforming a number of competitive baselines. The thorough analysis further demonstrates the effectiveness of our model compared to explicit annotation projection approaches.

Existing approaches for sarcasm detection are mainly based on supervised learning, in which the promising performance largely depends on a considerable amount of labeled data or extra information. In the real world scenario, however, the abundant labeled data or extra information requires high labor cost, not to mention that sufficient annotated data is unavailable in many low-resource conditions. To alleviate this dilemma, we investigate sarcasm detection from an unsupervised perspective, in which we explore a masking and generation paradigm in the context to extract the context incongruities for learning sarcastic expression. Further, to improve the feature representations of the sentences, we use unsupervised contrastive learning to improve the sentence representation based on the standard dropout. Experimental results on six perceived sarcasm detection benchmark datasets show that our approach outperforms baselines. Simultaneously, our unsupervised method obtains comparative performance with supervised methods for the intended sarcasm dataset.

In this paper, we bridge the heterogeneity gap between different modalities and improve image-text retrieval by taking advantage of auxiliary image-to-text and text-to-image generative features with contrastive learning. Concretely, contrastive learning is devised to narrow the distance between the aligned image-text pairs and push apart the distance between the unaligned pairs from both inter- and intra-modality perspectives with the help of cross-modal retrieval features and auxiliary generative features. In addition, we devise a support-set regularization term to further improve contrastive learning by constraining the distance between each image/text and its corresponding cross-modal support-set information contained in the same semantic category. To evaluate the effectiveness of the proposed method, we conduct experiments on three benchmark datasets (i.e., MIRFLICKR-25K, NUS-WIDE, MS COCO). Experimental results show that our model significantly outperforms the strong baselines for cross-modal image-text retrieval. For reproducibility, we submit the code and data publicly at: \urlhttps://github.com/Hambaobao/CRCGS.

Stance detection aims to identify the stance of the text towards a target. Different from conventional stance detection, Zero-Shot Stance Detection (ZSSD) needs to predict the stances of the unseen targets during the inference stage. For human beings, we generally tend to reason the stance of a new target by linking it with the related knowledge learned from the known ones. Therefore, in this paper, to better generalize the target-related stance features learned from the known targets to the unseen ones, we incorporate the targeted background knowledge from Wikipedia into the model. The background knowledge can be considered as a bridge for connecting the meanings between known targets and the unseen ones, which enables the generalization and reasoning ability of the model to be improved in dealing with ZSSD. Extensive experimental results demonstrate that our model outperforms the state-of-the-art methods on the ZSSD task.

Zero-shot stance detection (ZSSD) is challenging as it requires detecting the stance of previously unseen targets during the inference stage. Being able to detect the target-related transferable stance features from the training data is arguably an important step in ZSSD. Generally speaking, stance features can be grouped into target-invariant and target-specific categories. Target-invariant stance features carry the same stance regardless of the targets they are associated with. On the contrary, target-specific stance features only co-occur with certain targets. As such, it is important to distinguish these two types of stance features when learning stance features of unseen targets. To this end, in this paper, we revisit ZSSD from a novel perspective by developing an effective approach to distinguish the types (target-invariant/-specific) of stance features, so as to better learn transferable stance features. To be specific, inspired by self-supervised learning, we frame the stance-feature-type identification as a pretext task in ZSSD. Furthermore, we devise a novel hierarchical contrastive learning strategy to capture the correlation and difference between target-invariant and -specific features and further among different stance labels. This essentially allows the model to exploit transferable stance features more effectively for representing the stance of previously unseen targets. Extensive experiments on three benchmark datasets show that the proposed framework achieves the state-of-the-art performance in ZSSD.

Recently, advances in neural network approaches have achieved many successes in both sentiment classification and probabilistic topic modeling. On the one hand, latent topics derived from the global context of documents could be helpful in capturing more accurate word semantics and hence could potentially improve the sentiment classification accuracy. On the other hand, the word-level attention vectors obtained during the learning of sentiment classifiers could carry word-level polarity information and can be used to guide the discovery of topics in topic modeling. This paper proposes a multi-task learning framework which jointly learns a sentiment classifier and a topic model by making the word-level latent topic distributions in the topic model to be similar to the word-level attention vectors in sentiment classifiers through mutual learning. Experimental results on the Yelp and IMDB datasets verify the superior performance of the proposed framework over strong baselines on both sentiment classification and topic modeling. The proposed framework also extracts more interpretable topics compared to other conventional topic models and neural topic models.

Most existing aspect-based sentiment analysis (ABSA) research efforts are devoted to extracting the aspect-dependent sentiment features from the sentence towards the given aspect. However, it is observed that about 60% of the testing aspects in commonly used public datasets are unknown to the training set. That is, some sentiment features carry the same polarity regardless of the aspects they are associated with (aspect-invariant sentiment), which props up the high accuracy of existing ABSA models when inevitably inferring sentiment polarities for those unknown testing aspects. Therefore, in this paper, we revisit ABSA from a novel perspective by deploying a novel supervised contrastive learning framework to leverage the correlation and difference among different sentiment polarities and between different sentiment patterns (aspect-invariant/-dependent). This allows improving the sentiment prediction for (unknown) testing aspects in the light of distinguishing the roles of valuable sentiment features. Experimental results on 5 benchmark datasets show that our proposed approach substantially outperforms state-of-the-art baselines in ABSA. We further extend existing neural network-based ABSA models with our proposed framework and achieve improved performance.

Lifelong learning capabilities are crucial for sentiment classifiers to process continuous streams of opinioned information on the Web. However, performing lifelong learning is non-trivial for deep neural networks as continually training of incrementally available information inevitably results in catastrophic forgetting or interference. In this paper, we propose a novel i terative network p runing with uncertainty r egularization method for l ifelong s entiment classification (IPRLS), which leverages the principles of network pruning and weight regularization. By performing network pruning with uncertainty regularization in an iterative manner, IPRLS can adapt a single BERT model to work with continuously arriving data from multiple domains while avoiding catastrophic forgetting and interference. Specifically, we leverage an iterative pruning method to remove redundant parameters in large deep networks so that the freed-up space can then be employed to learn new tasks, tackling the catastrophic forgetting problem. Instead of keeping the old-tasks fixed when learning new tasks, we also use an uncertainty regularization based on the Bayesian online learning framework to constrain the update of old tasks weights in BERT, which enables positive backward transfer, i.e. learning new tasks improves performance on past tasks while protecting old knowledge from being lost. In addition, we propose a task-specific low-dimensional residual function in parallel to each layer of BERT, which makes IPRLS less prone to losing the knowledge saved in the base BERT network when learning a new task. Extensive experiments on 16 popular review corpora demonstrate that the proposed IPRLS method significantly outperforms the strong baselines for lifelong sentiment classification. For reproducibility, we submit the code and data at: \urlhttps://github.com/siat-nlp/IPRLS .

Recent AI research has witnessed increasing interests in automatically designing the architecture of deep neural networks, which is coined as neural architecture search (NAS). The automatically searched network architectures via NAS methods have outperformed manually designed architectures on some NLP tasks. However, training a large number of model configurations for efficient NAS is computationally expensive, creating a substantial barrier for applying NAS methods in real-life applications. In this paper, we propose to accelerate neural architecture search for natural language processing based on knowledge distillation (called KD-NAS). Specifically, instead of searching the optimal network architecture on the validation set conditioned on the optimal network weights on the training set, we learn the optimal network by minimizing the knowledge loss transferred from a pre-trained teacher network to the searching network based on Earth Mover's Distance (EMD). Experiments on five datasets show that our method achieves promising performance compared to strong competitors on both accuracy and searching speed. For reproducibility, we submit the code at: https://github.com/lxk00/KD-NAS-EMD.

Detecting sarcastic expressions could promote the understanding of natural language in social media. In this paper, we revisit sarcasm detection from a novel perspective, so as to account for the long-range literal sentiment inconsistencies. More concretely, we explore a novel scenario of constructing an affective graph and a dependency graph for each sentence based on the affective information retrieved from external affective commonsense knowledge and the syntactical information of the sentence. Based on it, an Affective Dependency Graph Convolutional Network (ADGCN) framework is proposed to draw long-range incongruity patterns and inconsistent expressions over the context for sarcasm detection by means with interactively modeling the affective and dependency information. Experimental results on multiple benchmark datasets show that our proposed approach outperforms the current state-of-the-art methods in sarcasm detection.

In this paper, we propose a novel abstractive text summarization method with hierarchical multi-scale abstraction modeling and dynamic memory (called MADY). First, we propose a hierarchical multi-scale abstraction modeling method to capture the temporal dependencies of the document from multiple hierarchical levels of abstraction, which mimics the process of how human beings comprehend an article by learning fine timescales for low-level abstraction layers and coarse timescales for high-level abstraction layers. By applying this adaptive updating mechanism, the high-level abstraction layers are updated less frequently and expected to remember the long-term dependency better than the low-level abstraction layer. Second, we propose a dynamic key-value memory-augmented attention network to keep track of the attention history and comprehensive context information for the salient facets within the input document. In this way, our model can avoid generating repetitive words and faultiness summaries. Extensive experiments on two widely-used datasets demonstrate the effectiveness of the proposed MADY model in terms of both automatic evaluation and human evaluation. For reproducibility, we submit the code and data at: https://github.com/siat-nlp/MADY.git.

Target plays an essential role in stance detection of an opinionated review/claim, since the stance expressed in the text often depends on the target. In practice, we need to deal with targets unseen in the annotated training data. As such, detecting stance for an unknown or unseen target is an important research problem. This paper presents a novel approach that automatically identifies and adapts the target-dependent and target-independent roles that a word plays with respect to a specific target in stance expressions, so as to achieve cross-target stance detection. More concretely, we explore a novel solution of constructing heterogeneous target-adaptive pragmatics dependency graphs (TPDG) for each sentence towards a given target. An in-target graph is constructed to produce inherent pragmatics dependencies of words for a distinct target. In addition, another cross-target graph is constructed to develop the versatility of words across all targets for boosting the learning of dominant word-level stance expressions available to an unknown target. A novel graph-aware model with interactive Graphical Convolutional Network (GCN) blocks is developed to derive the target-adaptive graph representation of the context for stance detection. The experimental results on a number of benchmark datasets show that our proposed model outperforms state-of-the-art methods in cross-target stance detection.

In most previous studies, the aspect-related text is considered an important clue for the Aspect-based Sentiment Analysis (ABSA) task, and thus various attention mechanisms have been proposed to leverage the interactions between aspects and context. However, it is observed that some sentiment expressions carry the same polarity regardless of the aspects they are associated with. In such cases, it is not necessary to incorporate aspect information for ABSA. More observations on the experimental results show that blindly leveraging interactions between aspects and context as features may introduce noises when analyzing those aspect-invariant sentiment expressions, especially when the aspect-related annotated data is insufficient. Hence, in this paper, we propose an Adversarial Multi-task Learning framework to identify the aspect-invariant/dependent sentiment expressions without extra annotations. In addition, we adopt a gating mechanism to control the contribution of representations derived from aspect-invariant and aspect-dependent hidden states when generating the final contextual sentiment representations for the given aspect. This essentially allows the exploitation of aspect-invariant sentiment features for better ABSA results. Experimental results on two benchmark datasets show that extending existing neural models using our proposed framework achieves superior performance. In addition, the aspect-invariant data extracted by the proposed framework can be considered as pivot features for better transfer learning of the ABSA models on unseen aspects.

Memory networks have shown expressive performance on aspect based sentiment analysis. However, ordinary memory networks only capture word-level information and lack the capacity for modeling complicated expressions which consist of multiple words. Targeting this problem, we propose a novel convolutional memory network which incorporates an attention mechanism. This model sequentially computes the weights of multiple memory units corresponding to multi-words. This model may capture both words and multi-words expressions in sentences for aspect-based sentiment analysis. Experimental results show that the proposed model outperforms the state-of-the-art baselines.

Noise in class labels of any training set can lead to poor classification results no matter what machine learning method is used. In this paper, we first present the problem of binary classification in the presence of random noise on the class labels, which we call class noise. To model class noise, a class noise rate is normally defined as a small independent probability of the class labels being inverted on the whole set of training data. In this paper, we propose a method to estimate class noise rate at the level of individual samples in real data. Based on the estimation result, we propose two approaches to handle class noise. The first technique is based on modifying a given surrogate loss function. The second technique eliminates class noise by sampling. Furthermore, we prove that the optimal hypothesis on the noisy distribution can approximate the optimal hypothesis on the clean distribution using both approaches. Our methods achieve over 87% accuracy on a synthetic non-separable dataset even when 40% of the labels are inverted. Comparisons to other algorithms show that our methods outperform state-of-the-art approaches on several benchmark datasets in different domains with different noise rates.

Transfer learning has been used as a machine learning method to make good use of available language resources for other resource-scarce languages. However, the cumulative class noise during iterations of transfer learning can lead to negative transfer which can adversely affect performance when more training data is used. In this paper, we propose a novel transfer learning method which can detect negative transfers. This approach detects high quality samples after certain iterations to identify class noise in new transferred training samples and remove them to reduce misclassifications. With the ability to detect bad training samples and remove them, our method can make full use of large unlabeled training data available in the target language. Furthermore, the most important contribution in this paper is the theory of class noise detection. Our new class noise detection method overcame the theoretic flaw of a previous method based on Gaussian distribution. We applied this transfer learning method with negative transfer detection to cross lingual opinion analysis. Evaluation on the NLP&CC 2013 cross-lingual opinion analysis dataset shows that the proposed approach outperforms the state-of-the-art systems.

This paper proposes a novel approach using a coarse-to-fine analysis strategy for sentence-level emotion classification which takes into consideration of similarities to sentences in training set as well as adjacent sentences in the context. First, we use intra-sentence based features to determine the emotion label set of a target sentence coarsely through the statistical information gained from the label sets of the k most similar sentences in the training data. Then, we use the emotion transfer probabilities between neighboring sentences to refine the emotion labels of the target sentences. Such iterative refinements terminate when the emotion classification converges. The proposed algorithm is evaluated on Ren-CECps, a Chinese blog emotion corpus. Experimental results show that the coarse-to-fine emotion classification algorithm improves the sentence-level emotion classification by 19.11% on the average precision metric, which outperforms the baseline methods.

This paper presents an opinion analysis system based on linguistic knowledge which is acquired from small-scale annotated text and raw topic-relevant Web page. Based on the observation on the annotated opinion corpus, some word-, collocation- and sentence-level linguistic features for opinion analysis are discovered. Supervised and unsupervised learning techniques are developed to learn these features from annotated text and raw relevant Web page, respectively. These features are then incorporated into a classifier based on support vector machine (SVM) to identify opinionated sentences and determine their polarities. Evaluations show that the proposed opinion analysis system, namely OA, achieved promising performance, which shows the effectiveness of linguistic knowledge learning from relevant Web page.