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.

Event extraction is a long-standing and challenging task in natural language processing, and existing studies mainly focus on extracting events within sentences. However, a significant problem that has not been carefully investigated is whether an “event topic” can be identified to represent the main aspects of extracted events. This article formulates the “topic event” extraction problem, aiming to identify a representative event from extracted ones. Specifically, after defining the topic event, we develop a multifocal graph-based framework to handle the extraction task. To enrich the associations of events and their tokens, we construct four event graphs, including the event subgraph and three event-associated graphs (i.e., event dependency parsing graph, event organization graph, and event share token graph), that reflect the internal and external structures of events, respectively. Subsequently, we design a multi-attention event-graph neural network to capture these event graph structures and improve event subgraph embedding. Finally, the output embeddings in the last layer of each channel are concatenated and fed into a fully connected network for topic event recognition. Extensive experiments validate the effectiveness of our method, and the results confirm its superiority over state-of-the-art baselines. In-depth analyses explore the essential factors (e.g., graph structures, attentions, feature generation method, etc.) determining the extraction performance.

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 article 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 F 1 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.

Learning topic hierarchies from a multi-domain corpus is crucial in topic modeling as it reveals valuable structural information embedded within documents. Despite the extensive literature on hierarchical topic models, effectively discovering inter-topic correlations and differences among subtopics at the same level in the topic hierarchy, obtained from multiple domains, remains an unresolved challenge. This article proposes an enhanced nested Chinese restaurant process (nCRP), nCRP+, by introducing an additional mechanism based on Chinese restaurant franchise (CRF) for aspect-sharing pattern extraction in the original nCRP. Subsequently, by employing the distribution extracted from nCRP+ as the prior distribution for topic hierarchy in the hierarchical Dirichlet processes (HDP), we develop a hierarchical topic model for multi-domain corpus, named rHDP. We describe the model with the analogy of Chinese restaurant franchise based on the central kitchen and propose a hierarchical Gibbs sampling scheme to infer the model. Our method effectively constructs well-established topic hierarchies, accurately reflecting diverse parent-child topic relationships, explicit topic aspect sharing correlations for inter-topics, and differences between these shared topics. To validate the efficacy of our approach, we conduct experiments using a renowned public dataset and an online collection of Chinese financial documents. The experimental results confirm the superiority of our method over the state-of-the-art techniques in identifying multi-domain topic hierarchies, according to multiple evaluation metrics.

Event extraction is an essential task in natural language processing. Although extensively studied, existing work shares issues in three aspects, including (1) the limitations of using original syntactic dependency structure, (2) insufficient consideration of the node level and type information in Graph Attention Network (GAT), and (3) insufficient joint exploitation of the node dependency type and part-of-speech (POS) encoding on the graph structure. To address these issues, we propose a novel framework for open event extraction in documents. Specifically, to obtain an enhanced dependency structure with powerful encoding ability, our model is capable of handling an enriched parallel structure with connected ellipsis nodes. Moreover, through a bidirectional dependency parsing graph, it considers the sequence of order structure and associates the ancestor and descendant nodes. Subsequently, we further exploit node information, such as the node level and type, to strengthen the aggregation of node features in our GAT. Finally, based on the coordination of triple-channel features (i.e., semantic, syntactic dependency and POS), the performance of event extraction is significantly improved. Extensive experiments are conducted to validate the effectiveness of our method, and the results confirm its superiority over the state-of-the-art baselines. Furthermore, in-depth analyses are provided to explore the essential factors determining the extraction performance.

With the rapid development of Radio Frequency Identification (RFID), sensor and wireless technologies, a large amount of trajectory data of moving objects are emerging, and trajectory data mining has received more and more attentions recently. However, since the data collected by sensors and RFID readers are usually noisy, it is necessary and meaningful to clean up the noise, including missing detection events and cross detection events, so as to provide high quality data for various applications using trajectory data. Cleaning up the trajectory events should take into account of uncertainty of location and unreliability of event detection at the same time. In the paper, we first discuss the rules to distinguish between normal detection events and false detection events in the trajectories, using constraints on continuous motion between adjacent detection regions and direct moving time between neighboring physical regions. Then, as a unified cleaning framework, we establish a probabilistic region connection graph to represent region detection features, region connection relationships, and region transition probabilities of neighboring physical regions. Focusing on interpolating missing events, we suggest two path-based probabilistic interpolating strategies, namely, the Most Likely Path (MLP) strategy and the Highest Weighting Probability Path (HWPP) strategy. Also, we discuss pruning rules of candidate paths for reducing computational cost. Finally, we conduct experiments over simulation data to demonstrate the effectiveness and efficiency of the proposed methods.

In XML retrieval, nodes with different tags play different roles in XML documents and then tags should be reflected in the relevance ranking. An automatic method is proposed in this paper to infer the weights of tags. We first investigate 15 features about tags, and then select five of them based on the correlations between these features and manual tag weights. Using these features, a tag weight assignment model, ATG, is designed. We evaluate the performance of ATG on two real data sets, IEEECS and Wikipedia from two different perspectives. One is to evaluate the quality of the model by measuring the correlation between weights generated by our model and those given by experts. The other is to test the effectiveness of the model in improving retrieval performance. Experimental results show that the tag weights generated by ATG are highly correlated with the manually assigned weights and the ATG model improves retrieval effectiveness significantly.