Yan-Qin Liu

Yan-Qin Liu

Auto-generated profile, based on publicly available information

Yan-Qin Liu

College of Computer and Data Science, Fuzhou University, Fuzhou, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 December 2024 in IEEE Transactions on Cognitive and Developmental Systems
Verified
Journal Article
Closed access
GZGui-Huang Zeng
Gui-Huang Zeng
YLYan-Qin Liu
Yan-Qin Liu
CZChun-Yang Zhang
Chun-Yang Zhang
HCHai-Chun Cai
Hai-Chun Cai
CCC.L. Philip Chen
C.L. Philip Chen
The goal of multi-document summarization (MDS) is to generate a comprehensive and concise summary from multiple documents, which should not only be grammatically correct but also semantically contains the refined content of the overall texts. Existing summarizers based on sequential pre-trained large language models often cognize documents as linear sequences, which overlook the hierarchical structure correlations of sentences and paragraphs within or between documents. Additionally, those models also have limitations in handling long text input. To alleviate these two problems, a multi-document summarization model is proposed, with a heterogeneous graph of sentences, paragraphs and documents, called HeterMDS, to uncover deep semantic meanings and local-global context within documents. By integrating large language model and graph encoder with bootstrapped graph latents, the proposed HeterMDS can learn a semantically rich document representation and generate a coherent, concise and fact-consistent summary. It can be flexibly applied to current pre-trained language models, effectively improving their performance in MDS. Extensive experiment results can verify the effectiveness of the proposed HeterMDS and its contained modules, and demonstrate its competitiveness against the state-of-the-art models.