Predicate-argument based Bi-encoder for paraphrase identification

Peng, Qiwei, Weir, David, Weeds, Julie and Chai, Yekun (2022) Predicate-argument based Bi-encoder for paraphrase identification. 60th Annual Meeting of the Association for Computational Linguistics, Dublin, Ireland, 22nd - 27th May 2022. Published in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 1 5579-5589. Association for Computational Linguistics

[img] PDF - Published Version
Available under License Creative Commons Attribution.

Download (391kB)
[img] PDF - Accepted Version
Available under License Creative Commons Attribution.

Download (358kB)

Abstract

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.

Item Type: Conference Proceedings
Schools and Departments: School of Engineering and Informatics > Informatics
Related URLs:
SWORD Depositor: Mx Elements Account
Depositing User: Mx Elements Account
Date Deposited: 28 Mar 2022 10:03
Last Modified: 24 May 2022 11:27
URI: http://sro.sussex.ac.uk/id/eprint/105056

View download statistics for this item

📧 Request an update