University of Sussex
Browse
2022.acl-long.382.pdf (382.52 kB)

Predicate-argument based Bi-encoder for paraphrase identification

Download (382.52 kB)
Version 2 2023-06-07, 08:57
Version 1 2023-06-07, 07:54
conference contribution
posted on 2023-06-07, 08:57 authored by Qiwei Peng, David WeirDavid Weir, Julie WeedsJulie Weeds, Yekun Chai
Paraphrase identification involves identifying whether a pair of sentences express the same or similar meanings. While cross-encoders have achieved high performances across several benchmarks, bi-encoders such as SBERT have been widely applied to sentence pair tasks. They exhibit substantially lower computation complexity and are better suited to symmetric tasks. In this work, we adopt a bi-encoder approach to the paraphrase identification task, and investigate the impact of explicitly incorporating predicate-argument information into SBERT through weighted aggregation. Experiments on six paraphrase identification datasets demonstrate that, with a minimal increase in parameters, the proposed model is able to outperform SBERT/SRoBERTa significantly. Further, ablation studies reveal that the predicate-argument based component plays a significant role in the performance gain.

History

Publication status

  • Published

File Version

  • Published version

Journal

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics

Publisher

Association for Computational Linguistics

Volume

1

Page range

5579-5589

Event name

60th Annual Meeting of the Association for Computational Linguistics

Event location

Dublin, Ireland

Event type

conference

Event date

22nd - 27th May 2022

Series

Long Papers

Department affiliated with

  • Informatics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2022-03-28

First Open Access (FOA) Date

2022-05-24

First Compliant Deposit (FCD) Date

2022-03-28

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC