181 publications from this institution
Disease prediction, aimed at predicting possible future diseases of patients, is a fundamental research problem in medical informatics. Many studies have proposed the introduction of external knowledge to enhance existing models with some effect, but since most of...
Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of external databases. This comprehensive review paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG. It meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval, the generation and the augmentation techniques. The paper highlights the state-of-the-art technologies embedded in each of these critical components, providing a profound understanding of the advancements in RAG systems. Furthermore, this paper introduces up-to-date evaluation framework and benchmark. At the end, this article delineates the challenges currently faced and points out prospective avenues for research and development.
Selectional Con straints are usually checked for detecting semantic relations. Previous work usually defined the constraints manually based on hand crafted concept taxonomy, which is time-consuming and impractical for large scale relation extraction....
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...
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.
In this paper, we are the first to construct a software programming taxonomy from Stackoverflow. More precisely, we propose a machine learning based method with novel features to capture the hierarchical semantic structure of tags in Stackoverflow. A graph pruning algorithm is applied to eliminate the conflicts by constructing a Directed Acyclic Graph (DAG). As a result, our dataset, named Software.zhishi.schema, contains 38,205 concepts together with 36,249 subsumption relations. In order to further test the usability of our published data, we adopt a similarity computing task of words from software programming which is one of the most fundamental tasks in the software repository mining area. The results show that our dataset can outperform other knowledge bases due to its high coverage with finergrained domain concepts.
With the development of the Semantic Web, more and more ontologies are available for exploitation by semantic search engines. However, while semantic search engines support the retrieval of candidate ontologies, the final selection of the most appropriate ontology is...
