Changxuan Wan

Qizhi Wan, Changxuan Wan, Keli Xiao et al.

Document-level event extraction is a long-standing challenging information retrieval problem involving a sequence of sub-tasks: entity extraction, event type judgment, and event type-specific multi-event extraction. However, addressing the problem as multiple learning tasks leads to increased model complexity. Also, existing methods insufficiently utilize the correlation of entities crossing different events, resulting in limited event extraction performance. This paper introduces a novel framework for document-level event extraction, incorporating a new data structure called token-event-role and a multi-channel argument role prediction module. The proposed data structure enables our model to uncover the primary role of tokens in multiple events, facilitating a more comprehensive understanding of event relationships. By leveraging the multi-channel prediction module, we transform entity and multi-event extraction into a single task of predicting token-event pairs, thereby reducing the overall parameter size and enhancing model efficiency. The results demonstrate that our approach outperforms the state-of-the-art method by 9.5 percentage points in terms of the F1 score, highlighting its superior performance in event extraction. Furthermore, an ablation study confirms the significant value of the proposed data structure in improving event extraction tasks, further validating its importance in enhancing the overall performance of the framework.

Zhao Tan, Xiping Liu, Qing Shu et al.

Text-to-SQL translates natural language questions into executable SQL queries, enabling intuitive database access for non-experts. While large language models achieve strong performance on Text-to-SQL with prompting, they still struggle with complex queries that involve deeply nested logic or multiple clauses. A widely used approach employs SQL skeletons--intermediate representations of query logic--to streamline generation, but existing methods are limited by their reliance on a single structural hypothesis and lack of progressive reasoning. To overcome these limitations, we propose LEAF-SQL, a novel framework that reframes skeleton prediction as a coarse-to-fine tree search process. LEAF-SQL enables systematic exploration of diverse structural hypotheses with adaptive refinement. Several key techniques are employed in LEAF-SQL: (1) a three-level skeleton hierarchy to guide the search, (2) a Skeleton Formulation Agent to generate diverse candidates, and (3) a Skeleton Evaluation Agent to efficiently prune the search space. This integrated design yields skeleton candidates that are both structurally diverse and granularity-adaptive, providing a stronger foundation for the SQL generation. Extensive experiments show that LEAF-SQL consistently improves the performance of various LLM backbones. On the official hidden test set of the challenging BIRD benchmark, our method achieves 71.6 execution accuracy, which outperforms leading search-based and skeleton-based methods, affirming its effectiveness for complex queries.

Guoqiong Liao, Xiaomei Huang, Neal N. Xiong et al.

The importance of contexts has been widely recognized in recommender systems for individuals. However, most existing group recommendation models in Event-Based Social Networks (EBSNs) focus on how to aggregate group members' preferences to form group preferences. In these models, the influence of contexts on groups is considered but simply defined in a manual way, which cannot model the complex and deep interactions between contexts and groups. In this paper, we propose an Attention-based Context-aware Group Event Recommendation model (ACGER) in EBSNs. ACGER models the deep, non-linear influence of contexts on users, groups, and events through multi-layer neural networks. Especially, a novel attention mechanism is designed to enable the influence weights of contexts on users/groups change dynamically with the events concerned. Considering that groups may have completely different behavior patterns from group members, we propose that the preference of a group need to be obtained from indirect and direct perspectives (called indirect preference and direct preference respectively). In order to obtain the indirect preference, we propose a method of aggregating preferences based on attention mechanism. Compared with existing predefined strategies, this method can flexibly adapt the strategy according to the events concerned by the group. In order to obtain the direct preference, we employ neural networks to directly learn it from group-event interactions. Furthermore, to make full use of rich user-event interactions in EBSNs, we integrate the context-aware individual recommendation task into ACGER, which enhances the accuracy of learning of user embeddings and event embeddings. Extensive experiments on two real datasets from Meetup show that our model ACGER significantly outperforms the state-of-the-art models.