Disentangling Specificity for Abstractive Multi-document Summarization
Date
2024
Authors
Ma, C.
Zhang, W.E.
Wang, H.
Zhuang, H.
Guo, M.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
International Joint Conference on Neural Networks, 2024, pp.1-8
Statement of Responsibility
Congbo Ma, Wei Emma Zhang, Hu Wang, Haojie Zhuang, Mingyu Guo
Conference Name
International Joint Conference on Neural Networks (IJCNN) (30 Jun 2024 - 5 Jul 2024 : Yokohama, Japan)
Abstract
Multi-document summarization (MDS) generates a summary from a document set. Each document in a set describes topic-relevant concepts, while per document also has its unique contents. However, the document specificity receives little attention from existing MDS approaches. Neglecting specific information for each document limits the comprehensiveness of the generated summaries. To solve this problem, in this paper, we propose to disentangle the specific content from documents in one document set. The document-specific representations, which are encouraged to be distant from each other via a proposed orthogonal constraint, are learned by the specific representation learner. We provide extensive analysis and have interesting findings that specific information and document set representations contribute distinctive strengths and their combination yields a more comprehensive solution for the MDS. Also, we find that the common (i.e. shared) information could not contribute much to the overall performance under the MDS settings. Implemetation codes are available at https://github.com/congboma/DisentangleSum.
School/Discipline
Dissertation Note
Provenance
Description
Part of WCCI 2024 - Featuring three conferences under one roof: IJCNN, FUZZ-IEEE, and IEEE CEC.
Access Status
Rights
©2024 IEEE