Publications

Retrieval Augmented Generation (RAG) has emerged as a promising solution to address hallucination issues in Large Language Models (LLMs). However, the integration of multiple retrieval sources, while potentially more informative, introduces new challenges that can paradoxically exacerbate hallucination problems. These challenges manifest primarily in two aspects: the sparse distribution of multi-source data that hinders the capture of logical relationships and the inherent inconsistencies among different sources that lead to information conflicts. To address these challenges, we propose MultiRAG, a novel framework designed to mitigate hallucination in multi-source retrieval-augmented generation through knowledge-guided approaches. Our framework introduces two key innovations: (1) a knowledge construction module that employs multi-source line graphs to efficiently aggregate logical relationships across different knowledge sources, effectively addressing the sparse data distribution issue; and (2) a sophisticated retrieval module that implements a multi-level confidence calculation mechanism, performing both graph-level and node-level assessments to identify and eliminate unreliable information nodes, thereby reducing hallucinations caused by inter-source inconsistencies. Extensive experiments on four multi-domain query datasets and two multi-hop QA datasets demonstrate that MultiRAG significantly enhances the reliability and efficiency of knowledge retrieval in complex multi-source scenarios. Our code is available in https://github.com/wuwenlong123/MultiRAG.

In this paper, we propose fuzzy pD* semantics which generalizes pD* semantics to reason over fuzzy RDF data using OWL vocabulary. We first define the notions of fuzzy RDF graph and fuzzy pD* interpretation. We then present a set of fuzzy pD*entailment rules and define the Best Degree Bound (BDB) of a triple derived from a fuzzy RDF graph. We show the existence of the BDB of an arbitrary triple. After that, we generalize the partial and full pD* closures to obtain the BDBs of derived triples. We show that the partial fuzzy closure exists and can be computed within polynomial time. Finally, we prove soundness and completeness results for the entailment relation. We also prove that the consistency checking is in P, the entailment is NP-complete, and in P if the target fuzzy RDF graph is ground. Therefore, extending the pD* semantics with fuzzy semantics does not increase the computational complexity.

Competitor identification tries to find competitors of some entity in a given field, which is the key to the success of market intelligence. Manually collecting competitors is labor-intensive and time consuming. So automatic approaches are proposed for this purpose....

More and more structured information in the form of semantic data is nowadays available. It offers a wide range of new possibilities especially for semantic search and Web data integration. However, their effective exploitation still brings about a number of challenges, e.g. usability, scalability and uncertainty. In this paper, we present Dataplorer, a solution designed to address these challenges. We consider the usability through the use of hybrid queries and faceted search, while still preserving the scalability thanks to an extension of inverted index to support this type of query. Moreover, Dataplorer deals with uncertainty by means of a powerful ranking scheme to find relevant results. Our experimental results show that our proposed approach is promising and it makes us believe that it is possible to extend the current IR infrastructure to query and search the Web of data.

Sentence alignment is an enabling technology which extracts mass of bilingual corpora automatically from the vast and ever-growing Web pages. In this paper, we propose a novel graph-based sentence alignment approach. Compared with the existing approaches, ours is...

The Web contains a large amount of documents and an increasing quantity of structured data in the form of RDF triples. Many of these triples are annotations associated with documents. While structured queries constitute the principal means to retrieve structured data, keyword queries are typically used for document retrieval. Clearly, a form of hybrid search that seamlessly integrates these formalisms to query both textual and structured data can address more complex information needs. However, hybrid search on the large scale Web environment faces several challenges. First, there is a need for repositories that can store and index a large amount of semantic data as well as textual data in documents, and manage them in an integrated way. Second, methods for hybrid query answering are needed to exploit the data from such an integrated repository. These methods should be fast and scalable, and in particular, they shall support flexible ranking schemes to return not all but only the most relevant results. In this paper, we present CE2, an integrated solution that leverages mature information retrieval and database technologies to support large scale hybrid search. For scalable and integrated management of data, CE2 integrates off-the-shelf database solutions with inverted indexes. Efficient hybrid query processing is supported through novel data structures and algorithms which allow advanced ranking schemes to be tightly integrated. Furthermore, a concrete ranking scheme is proposed to take features from both textual and structured data into account. Experiments conducted on DBpedia and Wikipedia show that CE2 can provide good performance in terms of both effectiveness and efficiency.

Knowledge Representation Learning (KRL) is crucial for enabling applications of symbolic knowledge from Knowledge Graphs (KGs) to downstream tasks by projecting knowledge facts into vector spaces. Despite their effectiveness in modeling KG structural information, KRL methods are suffering from the sparseness of KGs. The rise of Large Language Models (LLMs) built on the Transformer architecture presents promising opportunities for enhancing KRL by incorporating textual information to address information sparsity in KGs. LLM-enhanced KRL methods, including three key approaches, encoder-based methods that leverage detailed contextual information, encoder-decoder-based methods that utilize a unified Seq2Seq model for comprehensive encoding and decoding, and decoder-based methods that utilize extensive knowledge from large corpora, have significantly advanced the effectiveness and generalization of KRL in addressing a wide range of downstream tasks. This work provides a broad overview of downstream tasks while simultaneously identifying emerging research directions in these evolving domains.

Paradigm Shift of Library Industry in China As more and more readers are in favor of accessing digital resources online, most libraries in China are in their way to build or strengthen their digital libraries. Nowadays, there exist several major content providers like WeiPu4, WanFang5, and ChaoXing6 who not only own a large number of digital contents of journals, books, andmagazines, but also run their integrated platforms for search and navigation. Most libraries only act as a consumer or a distributor in the digital content supply chain, which makes them suffer from serious homogenization, lack of content control, and weak competitiveness. The above issues enforce libraries to search for new opportunities. On the other hand, in early 2013, China Ministry of Culture has issued guidelines to build various resource repositories specified for different sectors. It advocated different regions to develop thematic repositories according to the economic and cultural characteristics of the region. ZhouShan Library takes this chance and becomes a pioneer to make the transition. ZhouShan Islands are listed as the first “state-level new district” around marine economy.With the support of local government, ZhouShan Library starts a project named “Universal Knowledge Repository for Marine Digital Library”. The intension is to help inhabitants and travelers know ZhouShan and marine economy, and to support different bureaus of ZhouShan government, such as Fishery Agency or Economic and Information Commission to do queries and statistics about local marine economy. In this way, ZhouShan Library is changing from a content distributor to a content provider of the marine domain. This change also happens to other regional libraries, which leads to a trend of paradigm shift in China’s library industry. TheRole of (Vertical)KnowledgeGraphRegarding the ZhouShan Library project, a marine repository should include fishes, fishing grounds, fish processing methods, related researchers and local enterprises. No single source can cover all aspects of data in the repository. It is also impossible for users to manually integrate knowledge from various sources. In some cases, concepts or facts need to be extracted from semi-structured data (e.g., lists or tables from Web pages) and unstructured data (e.g., documents). In other cases, data from internal database or from LOD are to be extracted, transformed, and loaded to the repository in a unified representation. Moreover, research institutes,

Recently, a growing number of linguistic resources in different languages have been published and interlinked as part of the Linguistic Linked Open Data (LLOD) cloud. However, in comparison to English and other prominent languages, the presence of Chinese in such a...