Multimodal sarcasm detection is a critical and challenging task that requires understanding the implicit associations between images and text. The existing multimodal sarcasm detection methods frequently overlook implicit sarcastic cues and are inadequate in modeling complex inter-modal conflicts. To address these limitations, we propose a novel framework, termed Sarcasm Detection with Sarcasm Cues and Hypergraph (SCH-SD). Specifically, we design prompt templates to leverage a Multimodal Large Language Model (MLLM) for generating detailed image descriptions and extracting implicit sarcastic cues from the input samples. Next, we apply a shallow cross-modal fusion mechanism to the encoded features to facilitate preliminary cross-modal interactions. Finally, we design a hypergraph-based deep cross-modal information fusion module to model the complex conflicting information between different modalities. Experimental results on the public benchmarks MMSD1.0 and MMSD2.0 demonstrate that SCH-SD outperforms existing baselines, improving Acc by 1.68% and 0.83%, and F1 by 2.77% and 1.98%, respectively, achieving state-of-the-art performance.

Implicit sentiment analysis (ISA) is particularly sensitive to user characteristics due to the absence of explicit sentiment cues. While existing approaches leverage explicit user attributes and social relationships, they neglect the implicit interest preferences embedded in user content and multimodal commonsense knowledge. This article introduces a novel personalized ISA framework that systematically integrates heterogeneous user knowledge with multimodal commonsense to address this limitation. Our core innovation lies in a multi-stage knowledge integration pipeline that first captures rich semantic representations through a large language model, then constructs a comprehensive user profile by fusing multiple views of implicit interests derived from user-multimodal commonsense-content interactions. Specifically, we employ graph neural networks to distill structured knowledge from automatically constructed multimodal commonsense graphs, which enhances semantic understanding. The different perspectives of user interests are then systematically fused to capture implicit preference characteristics. Finally, we introduce an adaptive gated fusion mechanism that dynamically incorporates heterogeneous user knowledge and multimodal commonsense into implicit sentiment semantics, enabling personalized analysis capabilities. Extensive experiments on two public personalized ISA Chinese datasets demonstrate that our method outperforms baselines by at least 2.86% and 3.03%, respectively, validating its effectiveness in comprehensive and personalized modeling of implicit sentiment.

Event Causality Extraction (ECE) aims to extract causal event pairs from text. Existing methods overlook the interplay between causal event pairs and their corresponding textual evidence (e.g., causal event mention pairs), and fail to effectively leverage global causal dependency information. To address these issues, we propose a Mention-Level Causal Evidence and Global Causal Graph Reasoning (MLCE-GCGR) framework to enhance ECE. First, we introduce an auxiliary Event Mention Causality Extraction (EMCE) task, which extracts causal event mention pairs, to provide evidence for the main ECE task, and design a Dual-Level Interaction Enhancement (DLIE) strategy to enhance the bidirectional interplay between event-level and mention-level causality. Second, we develop a Global Causal Graph Reasoning (GCGR) module that simulates human-like multi-turn reasoning, aiming to progressively refine the causal graph by capturing global dependencies among event mentions, types, and arguments. Experiments on four benchmark datasets show that our method outperforms state-of-the-art approaches. Moreover, by extracting causal event mention pairs as supporting evidence, our approach improves the interpretability of structured causality extraction.

The subtlety of emotional expressions makes implicit emotion analysis (IEA) particularly sensitive to user-specific characteristics. Current studies personalize emotion analysis by focusing on the author but neglect the impact of the intended reader on implicit emotional feedback. In this paper, we introduce Personalized IEA (PIEA) and present the RAPPIE model, which addresses subjective variability by incorporating reader feedback. In particular, (1) we create reader agents based on large language models to simulate reader feedback, overcoming the issue of “spiral of silence effect” and data incompleteness of real reader reaction. (2) We develop a role-aware multi-view graph learning to model the emotion interactive propagation process in scenarios with sparse reader information. (3) We construct two new PIEA datasets covering English and Chinese social media with detailed user metadata, addressing the text-centric limitation of existing datasets. Extensive experiments show that RAPPIE significantly outperforms state-of-the-art baselines, demonstrating the value of incorporating reader feedback in PIEA.

Clinical event extraction involves extracting event attributes from clinical medical records. However, arguments involved in clinical events exhibit specificity, diversity and ambiguity, posing substantial challenges for existing models. The scarcity of Chinese clinical datasets further impedes research on clinical event extraction. Existing models commonly experience issues of contextual information decay during multi-task processes. Furthermore, unlike entities in general domains, medical entities are expressed in complex ways, resulting in low recall. To address these challenges, we propose a Clinical Event Extraction model based on Contextual ResiduAl and Soft Encoding Relation Extraction(CARE), which consists of an encoding module, a relation detection module, and an entity recognition module. The relation detection module identifies potential relations within a medical record. To prevent error propagation in relation extraction, a soft encoding strategy is proposed to discern target relations from candidate ones. The entity recognition module employs the contextual residual connection mechanism to concatenate the text with relation between semantic templates before feeding them into the entity recognition module. On CHIP-CDEE and CEMRs, CARE achieves F1 scores of 73.22% and 94.83%, respectively, which outperforms all baseline models, including LLMs, demonstrating its effectiveness for this task.

Large Language Models (LLMs) demonstrate remarkable potential in Event Argument Extraction (EAE) tasks due to their powerful capabilities in contextual understanding and semantic generation. However, the absence of event schema knowledge limits their performance in these tasks. Additionally, we observe a strong correlation between argument roles and entity types, which is often disregarded in prevailing models. To address these challenges, we propose FINE, a prompt tuning approach Fused with InterNal and External knowledge for low-resource EAE based on generative framework with LLM, which integrates global event schema knowledge and local entity information. Specifically, FINE employs External Knowledge (EK) Prompt Generator to construct external knowledge prompts with high event-awareness, which can help better capture the semantics of roles and their diversity among various events. Furthermore, we propose RAEA, a Role-Associated Entity Argument candidate mechanism to filter relevant entities within the context, effectively reducing interference from irrelevant entities. Experimental results on ACE05-EN and ERE-EN datasets demonstrate that our proposed FINE model achieves significant improvements in EAE, particularly in low-resource scenarios.

Event Causality Extraction (ECE) aims to extract the cause-effect event pairs with their structured event information from plain texts. As far as we know, the existing ECE methods mainly focus on the correlation between arguments, without explicitly modeling the causal relationship between events, and usually design two independent frameworks to extract cause events and effect events, respectively, which cannot effectively capture the dependency between the subtasks. Therefore, we propose a joint multi-label extraction framework for ECE to alleviate the above limitations. In particular, 1) we design a heterogeneous-relation-aware graph module to learn the potential relationships between events and arguments, in which we construct the heterogeneous graph by taking the predefined event types and all the words in the sentence as nodes, and modeling three relationships of "event-event", "event-argument" and "argument-argument" as edges. 2) We also design a multi-channel label enhancing module to better learn the distributed representation of each label in the multi-label extraction framework, and further enhance the interaction between the subtasks by considering the preliminary results of cause-effect type identification and event argument extraction. The experimental results on the benchmark dataset ECE-CCKS show that our approach outperforms previous state-of-the-art methods, and that our model also performs well on the complex samples with multiple cause-effect event pairs.

Document-level Event Extraction (DEE) is a vital task in NLP as it seeks to automatically recognize and extract event information from a document. However, current approaches often overlook intricate relationships among events and subtle correlations among arguments within a document, which can significantly impact the effectiveness of event type recognition and the extraction of cross-sentence arguments in DEE task. This paper proposes a novel Correlation Association Interactive Network (CAINet), comprising two key components: event relationship graph and argument correlation graph. In particular, the event relationship graph models the relationship among various events through structural associations among event nodes and sentence nodes, to improve the accuracy of event recognition. On the other hand, the arguments correlation graph models the correlations among arguments by quantifying the strength of association among arguments, to effectively aggregate cross-sentence arguments, contributing to the overall success of DEE. Furthermore, we use the large language model to execute DEE task experiments. Experimental results show the proposed CAINet outperforms existing state-of-the-art models and large language models in terms of F1-score across two benchmark datasets.

Document-level event extraction has become one of the important research directions in natural language processing, which aims to extract the complete event arguments from the whole document. However, existing models cannot fully utilize contextual semantic relations and sequential information in complex document-level scenarios, failing to mine the relational facts between multiple sentences and arguments. To address the above problems, we propose a heterogeneous graph interaction event extraction model fusing positional embedding and attention matrix called GPAIT. Firstly, contextual semantic relationships are enhanced between entities by constructing entity attention relationship matrix; Secondly, the attention matrix is combined to rectify the representation of heterogeneous graphs; Finally, positional embedding is fused into graphs to build a graph convolutional neural network that can better capture semantic sequential relationships. Experiments on ChFinAnn and COVID-19 News show that GPAIT outperforms other document-level event extraction methods in terms of F1 by 1.2% and 3.6% respectively.

Emotion inference in multi-turn conversations aims to predict the participant's emotion in the next upcoming turn without knowing the participant's response yet, and is a necessary step for applications such as dialogue planning.However, it is a severe challenge to perceive and reason about the future feelings of participants, due to the lack of utterance information from the future.Moreover, it is crucial for emotion inference to capture the characteristics of emotional propagation in conversations, such as persistence and contagiousness.In this study, we focus on investigating the task of emotion inference in multi-turn conversations by modeling the propagation of emotional states among participants in the conversation history, and propose an addresseeaware module to automatically learn whether the participant keeps the historical emotional state or is affected by others in the next upcoming turn.In addition, we propose an ensemble strategy to further enhance the model performance.Empirical studies on three different benchmark conversation datasets demonstrate the effectiveness of the proposed model over several strong baselines.

Detecting public sentiment drift is a challenging task due to sentiment change over time.Existing methods first build a classification model using historical data and subsequently detect drift if the model performs much worse on new data.In this paper, we focus on distribution learning by proposing a novel Hierarchical Variational Auto-Encoder (HVAE) model to learn better distribution representation, and design a new drift measure to directly evaluate distribution changes between historical data and new data.Our experimental results demonstrate that our proposed model achieves better results than three existing state-of-theart methods.