Qiaosheng Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qiaosheng Chen has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Gong Cheng
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China
13 shared publications - Xiao Zhou
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China
6 shared publications - Jiageng Chen
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China
3 shared publications - Qing Shi
State Key Laboratory of Novel Software Technology, Nanjing University
3 shared publications - Weiqing Luo
Nanjing University
3 shared publications - Zhiyang Zhang
Nanjing University
3 shared publications
Latest Publications
- 26 September 2026
- Published by Springer Nature
- p. 99-115
DSEBench: A Test Collection for Explainable Dataset Search with Examples
- 26 September 2026
- Published by Springer Nature
- p. 99-115
DSEBench: A Test Collection for Explainable Dataset Search with Examples
- Open Access
- 29 August 2026
- Published by Springer Nature in Data Science and Engineering
- p. 1-21
CN-PDS: Facilitating Dataset Search with LLMs and its Application to China’s Public Data
- 29 August 2026
- Published by Springer Nature in Data Science and Engineering
- p. 1-21
Open AccessCN-PDS: Facilitating Dataset Search with LLMs and its Application to China’s Public Data
- Open Access
- 24 February 2026
- Published by Elsevier in Journal of Web Semantics
- Vol. 89
Caddie: A prototype of content-based ad hoc RDF dataset retrieval
- 24 February 2026
- Published by Elsevier in Journal of Web Semantics
- Vol. 89
Open AccessCaddie: A prototype of content-based ad hoc RDF dataset retrieval
- 29 October 2025
- Published by Springer Nature
- p. 3-21
mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
- 29 October 2025
- Published by Springer Nature
- p. 3-21
mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 116-126
μDS: Multi-Objective Data Snippet Extraction for Dataset Search
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 116-126
Open AccessμDS: Multi-Objective Data Snippet Extraction for Dataset Search
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 3433-3443
Benchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 3433-3443
Open AccessBenchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph
- Open Access
Benchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph
The rapid growth of open source machine learning (ML) resources, such as models and datasets, has accelerated IR research. However, existing platforms like Hugging Face do not explicitly utilize structured representations, limiting advanced queries and analyses such as tracing model evolution and recommending relevant datasets. To fill the gap, we construct HuggingKG, the first large-scale knowledge graph built from the Hugging Face community for ML resource management. With 2.6 million nodes and 6.2 million edges, HuggingKG captures domain-specific relations and rich textual attributes. It enables us to further present HuggingBench, a multi-task benchmark with three novel test collections for IR tasks including resource recommendation, classification, and tracing. Our experiments reveal unique characteristics of HuggingKG and the derived tasks. Both resources are publicly available, expected to advance research in open source resource sharing and management.
Open AccessBenchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph
The rapid growth of open source machine learning (ML) resources, such as models and datasets, has accelerated IR research. However, existing platforms like Hugging Face do not explicitly utilize structured representations, limiting advanced queries and analyses such as tracing model evolution and recommending relevant datasets. To fill the gap, we construct HuggingKG, the first large-scale knowledge graph built from the Hugging Face community for ML resource management. With 2.6 million nodes and 6.2 million edges, HuggingKG captures domain-specific relations and rich textual attributes. It enables us to further present HuggingBench, a multi-task benchmark with three novel test collections for IR tasks including resource recommendation, classification, and tracing. Our experiments reveal unique characteristics of HuggingKG and the derived tasks. Both resources are publicly available, expected to advance research in open source resource sharing and management.
- 27 November 2024
- Published by Springer Nature
- p. 78-97
DUNKS: Chunking and Summarizing Large and Heterogeneous Data for Dataset Search
- 27 November 2024
- Published by Springer Nature
- p. 78-97
DUNKS: Chunking and Summarizing Large and Heterogeneous Data for Dataset Search
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 303-312
ACORDAR 2.0: A Test Collection for Ad Hoc Dataset Retrieval with Densely Pooled Datasets and Question-Style Queries
Dataset search, or more specifically, ad hoc dataset retrieval which is a trending specialized IR task, has received increasing attention in both academia and industry. While methods and systems continue evolving, existing test collections for this task exhibit shortcomings, particularly suffering from lexical bias in pooling and limited to keyword-style queries for evaluation. To address these limitations, in this paper, we construct ACORDAR 2.0, a new test collection for this task which is also the largest to date. To reduce lexical bias in pooling, we adapt dense retrieval models to large structured data, using them to find an extended set of semantically relevant datasets to be annotated. To diversify query forms, we employ a large language model to rewrite keyword queries into high-quality question-style queries. We use the test collection to evaluate popular sparse and dense retrieval models to establish a baseline for future studies. The test collection and source code are publicly available.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 303-312
Open AccessACORDAR 2.0: A Test Collection for Ad Hoc Dataset Retrieval with Densely Pooled Datasets and Question-Style Queries
Dataset search, or more specifically, ad hoc dataset retrieval which is a trending specialized IR task, has received increasing attention in both academia and industry. While methods and systems continue evolving, existing test collections for this task exhibit shortcomings, particularly suffering from lexical bias in pooling and limited to keyword-style queries for evaluation. To address these limitations, in this paper, we construct ACORDAR 2.0, a new test collection for this task which is also the largest to date. To reduce lexical bias in pooling, we adapt dense retrieval models to large structured data, using them to find an extended set of semantically relevant datasets to be annotated. To diversify query forms, we employ a large language model to rewrite keyword queries into high-quality question-style queries. We use the test collection to evaluate popular sparse and dense retrieval models to establish a baseline for future studies. The test collection and source code are publicly available.
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1093-1103
Enhancing Dataset Search with Compact Data Snippets
In light of the growing availability and significance of open data, the problem of dataset search has attracted great attention in the field of information retrieval. Nevertheless, current metadata-based approaches have revealed shortcomings due to the low quality and availability of dataset metadata, while the magnitude and heterogeneity of actual data hindered the development of content-based solutions. To address these challenges, we propose to convert different formats of structured data into a unified form, from which we extract a compact data snippet that indicates the relevance of the whole data. Thanks to its compactness, we feed it into a dense reranker to improve search accuracy. We also convert it back to the original format to be presented for assisting users in relevance judgment. The effectiveness of our approach has been demonstrated by extensive experiments on two test collections for dataset search.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1093-1103
Open AccessEnhancing Dataset Search with Compact Data Snippets
In light of the growing availability and significance of open data, the problem of dataset search has attracted great attention in the field of information retrieval. Nevertheless, current metadata-based approaches have revealed shortcomings due to the low quality and availability of dataset metadata, while the magnitude and heterogeneity of actual data hindered the development of content-based solutions. To address these challenges, we propose to convert different formats of structured data into a unified form, from which we extract a compact data snippet that indicates the relevance of the whole data. Thanks to its compactness, we feed it into a dense reranker to improve search accuracy. We also convert it back to the original format to be presented for assisting users in relevance judgment. The effectiveness of our approach has been demonstrated by extensive experiments on two test collections for dataset search.