Disentangling Specificity for Abstractive Multi-document Summarization

Simple item page
dc.contributor.authorMa, C.
dc.contributor.authorZhang, W.E.
dc.contributor.authorWang, H.
dc.contributor.authorZhuang, H.
dc.contributor.authorGuo, M.
dc.contributor.conferenceInternational Joint Conference on Neural Networks (IJCNN) (30 Jun 2024 - 5 Jul 2024 : Yokohama, Japan)
dc.date.issued2024
dc.descriptionPart of WCCI 2024 - Featuring three conferences under one roof: IJCNN, FUZZ-IEEE, and IEEE CEC.
dc.description.abstractMulti-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.
dc.description.statementofresponsibilityCongbo Ma, Wei Emma Zhang, Hu Wang, Haojie Zhuang, Mingyu Guo
dc.identifier.citationInternational Joint Conference on Neural Networks, 2024, pp.1-8
dc.identifier.doi10.1109/IJCNN60899.2024.10651001
dc.identifier.isbn979-8-3503-5932-9
dc.identifier.issn2161-4393
dc.identifier.issn2161-4407
dc.identifier.orcidMa, C. [0000-0002-3270-5609]
dc.identifier.orcidZhang, W.E. [0000-0002-0406-5974]
dc.identifier.orcidZhuang, H. [0000-0003-4387-6347]
dc.identifier.orcidGuo, M. [0000-0002-3478-9201]
dc.identifier.urihttps://hdl.handle.net/2440/148017
dc.language.isoen
dc.publisherIEEE
dc.relation.granthttp://purl.org/au-research/grants/arc/DP230100233
dc.relation.ispartofseriesIEEE International Joint Conference on Neural Networks (IJCNN)
dc.rights©2024 IEEE
dc.source.urihttps://ieeexplore.ieee.org/xpl/conhome/10649807/proceeding
dc.subjectMulti-document summarization; Deep neural network; Transformer
dc.titleDisentangling Specificity for Abstractive Multi-document Summarization
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Research Outputs