2022.acl-long.382.pdf (382.52 kB)
Predicate-argument based Bi-encoder for paraphrase identification
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 ChaiParaphrase 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 LinguisticsPublisher
Association for Computational LinguisticsPublisher URL
Volume
1Page range
5579-5589Event name
60th Annual Meeting of the Association for Computational LinguisticsEvent location
Dublin, IrelandEvent type
conferenceEvent date
22nd - 27th May 2022Series
Long PapersDepartment affiliated with
- Informatics Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2022-03-28First Open Access (FOA) Date
2022-05-24First Compliant Deposit (FCD) Date
2022-03-28Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC