Publications

Text-to-SQL aims at translating textual questions into the corresponding SQL queries. Aggregate tables are widely created for high-frequent queries. Although text-to-SQL has emerged as an important task, recent studies paid little attention to the task over aggregate tables. The increased aggregate tables bring two challenges: (1) mapping of natural language questions and relational databases will suffer from more ambiguity, (2) modern models usually adopt self-attention mechanism to encode database schema and question. The mechanism is of quadratic time complexity, which will make inferring more time-consuming as input sequence length grows. In this paper, we introduce a novel approach named WAGG for text-to-SQL over aggregate tables. To effectively select among ambiguous items, we propose a relation selection mechanism for relation computing. To deal with high computation costs, we introduce a dynamical pruning strategy to discard unrelated items that are common for aggregate tables. We also construct a new large-scale dataset SpiderwAGG extended from Spider dataset for validation, where extensive experiments show the effectiveness and efficiency of our proposed method with 4% increase of accuracy and 15% decrease of inference time w.r.t a strong baseline RAT-SQL.

Linguistic resources are essential for Language Learning applications. However, available resources are usually created in isolation, thus, they are scattered and need to be linked before they can be used for a specific task such as learning of a foreign language. To address these problems we present a new resource that link linguistic resources of multiple languages using the framework of Linguistic Linked Open Data (LLOD).

Research demonstrates that the proactivity of in-vehicle conversational assistants (IVCAs) can help to reduce distractions and enhance driving safety, better meeting users' cognitive needs. However, existing IVCAs struggle with user intent recognition and context awareness, which leads to suboptimal proactive interactions. Large language models (LLMs) have shown potential for generalizing to various tasks with prompts, but their application in IVCAs and exploration of proactive interaction remain under-explored. These raise questions about how LLMs improve proactive interactions for IVCAs and influence user perception. To investigate these questions systematically, we establish a framework with five proactivity levels across two dimensions—assumption and autonomy—for IVCAs. According to the framework, we propose a ``Rewrite + ReAct + Reflect'' strategy, aiming to empower LLMs to fulfill the specific demands of each proactivity level when interacting with users. Both feasibility and subjective experiments are conducted. The LLM outperforms the state-of-the-art model in success rate and achieves satisfactory results for each proactivity level. Subjective experiments with 40 participants validate the effectiveness of our framework and show the proactive level with strong assumptions and user confirmation is most appropriate.

Commit messages are natural language descriptions of code changes, which are important for software evolution such as code understanding and maintenance. However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i.e., good-practice commits), while the rest do not. On the basis of our empirical study, we discover that training on good-practice commits significantly contributes to the commit message generation. Motivated by this finding, we propose a novel knowledge-aware denoising learning method called KADEL. Considering that good-practice commits constitute only a small proportion of the dataset, we align the remaining training samples with these good-practice commits. To achieve this, we propose a model that learns the commit knowledge by training on good-practice commits. This knowledge model enables supplementing more information for training samples that do not conform to good practice. However, since the supplementary information may contain noise or prediction errors, we propose a dynamic denoising training method. This method composes a distribution-aware confidence function and a dynamic distribution list, which enhances the effectiveness of the training process. Experimental results on the whole MCMD dataset demonstrate that our method overall achieves state-of-the-art performance compared with previous methods. Our source code and data are available at https://github.com/DeepSoftwareAnalytics/KADEL

As an important step towards bootstrapping the Semantic Web, many efforts have been made to extract triples from Wikipedia because of its wide coverage, good organization and rich knowledge. One kind of important triples is about Wikipedia articles and their non-isa...

Thanks to the development of geographic information technology, geospatial representation learning based on POIs (Point-of-Interest) has gained widespread attention in the past few years. POI is an important indicator to reflect urban socioeconomic activities, widely used to extract geospatial information. However, previous studies often focus on a specific area, such as a city or a district, and are designed only for particular tasks, such as land-use classification. On the other hand, large-scale pre-trained models (PTMs) have recently achieved impressive success and become a milestone in artificial intelligence (AI). Against this background, this study proposes the first large-scale pre-training geospatial representation learning model called GeoBERT. First, we collect about 17 million POIs in 30 cities across China to construct pre-training corpora, with 313 POI types as the tokens and the level-7 Geohash grids as the basic units. Second, we pre-train GeoEBRT to learn grid embedding in self-supervised learning by masking the POI type and then predicting. Third, under the paradigm of “pre-training + fine-tuning”, we design five practical downstream tasks. Experiments show that, with just one additional output layer fine-tuning, GeoBERT outperforms previous NLP methods (Word2vec, GloVe) used in geospatial representation learning by 9.21% on average in F1-score for classification tasks, such as store site recommendation and working/living area prediction. For regression tasks, such as POI number prediction, house price prediction, and passenger flow prediction, GeoBERT demonstrates greater performance improvements. The experiment results prove that pre-training on large-scale POI data can significantly improve the ability to extract geospatial information. In the discussion section, we provide a detailed analysis of what GeoBERT has learned from the perspective of attention mechanisms.

With the ever-growing use of textual biomedical data, domain entity annotation has become very important in biomedicine. Previous works on annotating domain entities from biomedical references suffer from several issues, such as a data flexibility problem, language dependency, and limitations with respect to word sense disambiguation. Meanwhile, the Linked Open Data (LOD) Initiative aims at interlinking data from various open knowledge bases. The numbers of entities and properties describing semantic relationships between entities within the linked data cloud have become very large. In this paper, we propose a knowledge-incentive approach for entity annotation in biomedicine, and present Me Detect, a prototype system that we developed based on this approach. With this approach, we over-come the problems of previous works using LOD-based collective annotation. Finally, we present the results of experiments that verify the effectiveness and efficiency of our approach.

Large Language Models are increasingly deployed as autonomous agents for complex real-world tasks, yet existing systems often focus on isolated improvements without a unifying design for robustness and adaptability. We propose a generalist agent architecture that integrates three core components: a collective multi-agent framework combining planning and execution agents with critic model voting, a hierarchical memory system spanning working, semantic, and procedural layers, and a refined tool suite for search, code execution, and multimodal parsing. Evaluated on a comprehensive benchmark, our framework consistently outperforms open-source baselines and approaches the performance of proprietary systems. These results demonstrate the importance of system-level integration and highlight a path toward scalable, resilient, and adaptive AI assistants capable of operating across diverse domains and tasks.

Large language models (LLMs) have demonstrated their significant potential to be applied for addressing various application tasks. However, traditional recommender systems continue to face great challenges such as poor interactivity and explainability, which actually also hinder their broad deployment in real-world systems. To address these limitations, this paper proposes a novel paradigm called Chat-Rec (ChatGPT Augmented Recommender System) that innovatively augments LLMs for building conversational recommender systems by converting user profiles and historical interactions into prompts. Chat-Rec is demonstrated to be effective in learning user preferences and establishing connections between users and products through in-context learning, which also makes the recommendation process more interactive and explainable. What's more, within the Chat-Rec framework, user's preferences can transfer to different products for cross-domain recommendations, and prompt-based injection of information into LLMs can also handle the cold-start scenarios with new items. In our experiments, Chat-Rec effectively improve the results of top-k recommendations and performs better in zero-shot rating prediction task. Chat-Rec offers a novel approach to improving recommender systems and presents new practical scenarios for the implementation of AIGC (AI generated content) in recommender system studies.

In this article, the authors design two metric sets considering Richness and Correctness based on a quasi-formal conceptual representation. They also design a novel metric set on overlapped instances of different KBs to make the metric results comparable. Finally, they use random sampling techniques to reduce human efforts for assessing the correctness. The authors evaluate three large Chinese KBs including DBpedia Chinese, Zhishi.me and SSCO comparatively, and further compare them with English KBs in terms of data set qualities. They also compare different versions of DBpedia and YAGO. The findings in these KBs not only give a detailed report of the current situation of extracted KBs, but also show the effectiveness of their methods in assessing the quality of Web-Scale KBs comparatively.

With the rapid development of Semantic Web, more and more RDF repositories, such as Linking Open Data (LOD), are available on the web. Generally, there are two services provided for exploring those RDF repositories, one is the keyword lookup, and the other is the...