Abstract
Phrase alignment is the basis for modelling sentence pair interactions, such as paraphrase and textual entailment recognition. Most phrase alignments are compositional processes such that an alignment of a phrase pair is constructed based on the alignments of their child phrases. Nonetheless, studies have revealed that non-compositional alignments involving long-distance phrase reordering are prevalent in practice. We address the phrase alignment problem by combining an unordered tree mapping algorithm and phrase representation modelling that explicitly embeds the similarity distribution in the sentences onto powerful contextualized representations. Experimental results demonstrate that our method effectively handles compositional and non-compositional global phrase alignments. Our method significantly outperforms that used in a previous study and achieves a performance competitive with that of experienced human annotators.- Anthology ID:
- 2020.emnlp-main.125
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1611–1623
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.125
- DOI:
- 10.18653/v1/2020.emnlp-main.125
- Cite (ACL):
- Yuki Arase and Jun’ichi Tsujii. 2020. Compositional Phrase Alignment and Beyond. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1611–1623, Online. Association for Computational Linguistics.
- Cite (Informal):
- Compositional Phrase Alignment and Beyond (Arase & Tsujii, EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2020.emnlp-main.125.pdf