Subspace Representations for Soft Set Operations and Sentence Similarities

Yoichi Ishibashi, Sho Yokoi, Katsuhito Sudoh, Satoshi Nakamura


Abstract
In the field of natural language processing (NLP), continuous vector representations are crucial for capturing the semantic meanings of individual words. Yet, when it comes to the representations of sets of words, the conventional vector-based approaches often struggle with expressiveness and lack the essential set operations such as union, intersection, and complement. Inspired by quantum logic, we realize the representation of word sets and corresponding set operations within pre-trained word embedding spaces. By grounding our approach in the linear subspaces, we enable efficient computation of various set operations and facilitate the soft computation of membership functions within continuous spaces. Moreover, we allow for the computation of the F-score directly within word vectors, thereby establishing a direct link to the assessment of sentence similarity. In experiments with widely-used pre-trained embeddings and benchmarks, we show that our subspace-based set operations consistently outperform vector-based ones in both sentence similarity and set retrieval tasks.
Anthology ID:
2024.naacl-long.192
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3512–3524
Language:
URL:
https://aclanthology.org/2024.naacl-long.192
DOI:
10.18653/v1/2024.naacl-long.192
Bibkey:
Cite (ACL):
Yoichi Ishibashi, Sho Yokoi, Katsuhito Sudoh, and Satoshi Nakamura. 2024. Subspace Representations for Soft Set Operations and Sentence Similarities. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3512–3524, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Subspace Representations for Soft Set Operations and Sentence Similarities (Ishibashi et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.192.pdf