Trainable Hard Negative Examples in Contrastive Learning for Unsupervised Abstractive Summarization

Simple item page
dc.contributor.authorZhuang, H.
dc.contributor.authorZhang, W.E.
dc.contributor.authorDong, C.G.
dc.contributor.authorYang, J.
dc.contributor.authorSheng, Q.Z.
dc.contributor.conferenceConference of the European Chapter of the Association for Computational Linguistics (EACL) (17 Mar 2024 - 22 Mar 2024 : St. Julian’s, Malta)
dc.contributor.editorPurver, M.
dc.contributor.editorGraham, Y.
dc.date.issued2024
dc.description.abstractContrastive learning has demonstrated promising results in unsupervised abstractive summarization. However, existing methods rely on manually crafted negative examples, demanding substantial human effort and domain knowledge. Moreover, these human-generated negative examples may be poor in quality and lack adaptability during model training. To address these issues, we propose a novel approach that learns trainable negative examples for contrastive learning in unsupervised abstractive summarization, which eliminates the need for manual negative example design. Our framework introduces an adversarial optimization process between a negative example network and a representation network (including the summarizer and encoders). The negative example network is trained to synthesize hard negative examples that are close to the positive examples, driving the representation network to improve the quality of the generated summaries. We evaluate our method on two benchmark datasets for unsupervised abstractive summarization and observe significant performance improvements compared to strong baseline models.
dc.description.statementofresponsibilityHaojie Zhuang, Wei Emma Zhang, Chang George Dong, Jian Yang, Quan Z. Sheng
dc.identifier.citationProceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024), 2024 / Purver, M., Graham, Y. (ed./s), pp.1589-1600
dc.identifier.isbn9798891760936
dc.identifier.orcidZhuang, H. [0000-0003-4387-6347]
dc.identifier.orcidZhang, W.E. [0000-0002-0406-5974]
dc.identifier.orcidDong, C.G. [0009-0005-1495-6534]
dc.identifier.urihttps://hdl.handle.net/2440/145993
dc.language.isoen
dc.publisherAssociation for Computational Linguistics
dc.publisher.placeOnline
dc.relation.granthttp://purl.org/au-research/grants/arc/IE230100119
dc.rights© 2024 Association for Computational Linguistics
dc.source.urihttps://aclanthology.org/2024.findings-eacl.110/
dc.titleTrainable Hard Negative Examples in Contrastive Learning for Unsupervised Abstractive Summarization
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Research Outputs