Abstract
This work studies comparatively two typical sentence matching tasks: textual entailment (TE) and answer selection (AS), observing that weaker phrase alignments are more critical in TE, while stronger phrase alignments deserve more attention in AS. The key to reach this observation lies in phrase detection, phrase representation, phrase alignment, and more importantly how to connect those aligned phrases of different matching degrees with the final classifier. Prior work (i) has limitations in phrase generation and representation, or (ii) conducts alignment at word and phrase levels by handcrafted features or (iii) utilizes a single framework of alignment without considering the characteristics of specific tasks, which limits the framework’s effectiveness across tasks. We propose an architecture based on Gated Recurrent Unit that supports (i) representation learning of phrases of arbitrary granularity and (ii) task-specific attentive pooling of phrase alignments between two sentences. Experimental results on TE and AS match our observation and show the effectiveness of our approach.- Anthology ID:
- E17-1066
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Editors:
- Mirella Lapata, Phil Blunsom, Alexander Koller
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 699–709
- Language:
- URL:
- https://aclanthology.org/E17-1066
- DOI:
- Cite (ACL):
- Wenpeng Yin and Hinrich Schütze. 2017. Task-Specific Attentive Pooling of Phrase Alignments Contributes to Sentence Matching. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 699–709, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Task-Specific Attentive Pooling of Phrase Alignments Contributes to Sentence Matching (Yin & Schütze, EACL 2017)
- PDF:
- https://preview.aclanthology.org/naacl24-info/E17-1066.pdf
- Data
- SICK, WikiQA