Multi-domain Dialogue State Tracking (DST)requires discourse coherence that transcends independent slot-filling.Most existing approaches rely on statistical regularities within static schemas, failing to capture the semantic coordination governing simultaneous slot updates.In this paper, we propose Event-DST, which models latent events as cognitive organizing units to dynamically coordinate slot interactions.By projecting dialogue context into a continuous semantic space, our model induces a dynamic structural bias to enforce pragmatic consistency.This structural guidance is integrated via a dual-stream fusion strategy that balances top-down structural constraints with bottom-up textual precision.Experimental results on two benchmarks demonstrate the superiority of our framework, providing an interpretable and parameter-efficient path toward robust dialogue understanding.

Multi-intent spoken language understanding (SLU) can handle multiple intent utterances in real-world scenarios, which has gained increasing research attention. Despite promising results achieved by existing joint models, they (1) perform utterance-level or token-level intent detection, resulting in suboptimal performance due to fixed thresholds or voting mechanisms; (2) incorporate all predicted intents into each slot hidden state and execute parallel slot decoding, which lacks precise intent-slot alignment and overlooks sequential dependencies between slot tokens. In this paper, we propose a new framework to tackle these two issues. For the first issue, we utilize a global pointer with auxiliary tasks to achieve span-based intent detection. For the second issue, we leverage span-based predicted intents for precise intent-slot guidance and introduce rotational position encoding in the interaction module to explicitly model sequential dependencies for precise slot filling. Experimental results on two benchmarks demonstrate the superiority of our framework.

Multi-modal sarcasm detection (MSD) aims to identify sarcasm by analyzing inconsistencies across image-text pairs. Despite promising results achieved, existing methods predominantly focus on model-level improvements, while overlooking data-level challenges. In this paper, we introduce HACL, a Hybrid Adaptive Curriculum Learning framework for MSD. Concretely, we first propose a Hybrid Difficulty Measurer (HDM) that quantifies sarcasm difficulty at both representation and prediction levels, where representation-level difficulty captures cross-modal semantic conflicts, and prediction-level difficulty reflects model learning progress via smoothed loss. Furthermore, an Adaptive Weight Optimizer (AWO) is proposed to dynamically balance these two difficulty metrics, prioritizing implicit sarcasm cues and hard samples. Combined with a competence-based curriculum scheduler, HACL progressively trains models from easy to hard samples. Experiments on two benchmarks demonstrate state-of-the-art performance, with ablation studies validating the necessity of HDM and AWO. Further analyses highlight HACL’s generalizability on multi-modal sentiment analysis (MSA) and its superiority over large vision-language models (LVLMs).

Event argument extraction (EAE), a critical task in information extraction, aims to identify structured event information from textual sentences. However, existing Chinese EAE methods fail to effectively integrate prior semantic knowledge from event types and argument roles, resulting in suboptimal performance. Moreover, mainstream approaches exhibit limited generalization in few-shot argument recognition scenarios. To address these challenges, we propose an enhanced Machine Reading Comprehension (MRC)-based Cross-Domain Chinese Event Argument Extraction framework. Our approach systematically incorporates event-type descriptions and argument-driven question formulations into contextual representations through multi-head attention mechanisms, thereby enhancing hierarchical semantic understanding of events. Furthermore, we introduce a transfer learning strategy with boundary-aware optimization to mitigate poor boundary detection of arguments in low-resource settings. Extensive experiments on two Chinese event extraction benchmarks, ACE2005 and MEC, validate the effectiveness of our method. The proposed model achieves superior performance, improving F1 scores by 1.6% and 1.9% on argument extraction tasks, respectively. Notably, it demonstrates significant gains in few-shot argument extraction scenarios, outperforming existing baselines in cross-domain generalization.

Zhihong Zhu, Kefan Shen, Zhaorun Chen, Yunyan Zhang, Yuyan Chen, Xiaoqi Jiao, Zhongwei Wan, Shaorong Xie, Wei Liu, Xian Wu, Yefeng Zheng. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Most research on influence maximization focuses on the network structure features of the diffusion process but lacks the consideration of multi-dimensional characteristics. This paper proposes the attributed influence maximization based on the crowd emotion, aiming to apply the user’s emotion and group features to study the influence of multi-dimensional characteristics on information propagation. To measure the interaction effects of individual emotions, we define the user emotion power and the cluster credibility, and propose a potential influence user discovery algorithm based on the emotion aggregation mechanism to locate seed candidate sets. A two-factor information propagation model is then introduced, which considers the complexity of real networks. Experiments on real-world datasets demonstrate the effectiveness of the proposed algorithm. The results outperform the heuristic methods and are almost consistent with the greedy methods yet with improved time performance.

Event as the unit of human knowledge, has attracted more and more attention and high regards from the academia. Events-based knowledge extraction and representation extend concept-based knowledge process techniques largely. In order to represent event-based knowledge, this paper extends existing web ontology language, OWL, by introducing some new constructors and axioms related to event features. This paper firstly gives definitions about event and event relationships, and then proposes an Event-based Description Logic, EDL, as logic basic of extended OWL. The semantics of event constructors and axioms can be mapped to EDL. In the end, we give an event class description which shows that event-based knowledge can be expressed well in the extended OWL language.