Semantically driven sentence fusion: Modeling and evaluation

Eyal Ben-David, Orgad Keller, Eric Malmi, Idan Szpektor, Roi Reichart

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Sentence fusion is the task of joining related sentences into coherent text. Current training and evaluation schemes for this task are based on single reference ground-truths and do not account for valid fusion variants. We show that this hinders models from robustly capturing the semantic relationship between input sentences. To alleviate this, we present an approach in which ground-truth solutions are automatically expanded into multiple references via curated equivalence classes of connective phrases. We apply this method to a large-scale dataset and use the augmented dataset for both model training and evaluation. To improve the learning of semantic representation using multiple references, we enrich the model with auxiliary discourse classification tasks under a multi-tasking framework. Our experiments highlight the improvements of our approach over state-of-the-art models.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics Findings of ACL
Subtitle of host publicationEMNLP 2020
PublisherAssociation for Computational Linguistics (ACL)
Pages1491-1505
Number of pages15
ISBN (Electronic)9781952148903
StatePublished - 2020
Externally publishedYes
EventFindings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020 - Virtual, Online
Duration: 16 Nov 202020 Nov 2020

Publication series

NameFindings of the Association for Computational Linguistics Findings of ACL: EMNLP 2020

Conference

ConferenceFindings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020
CityVirtual, Online
Period16/11/2020/11/20

Bibliographical note

Publisher Copyright:
©2020 Association for Computational Linguistics

Funding

We would like to thank the members of the IE@Technion NLP group and Roee Aharoni, for their valuable feedback and advice. Roi Reichart was partially funded by ISF personal grant No. 1625/18.

FundersFunder number
Israel Science Foundation1625/18

    Fingerprint

    Dive into the research topics of 'Semantically driven sentence fusion: Modeling and evaluation'. Together they form a unique fingerprint.

    Cite this