Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations

James Y. Huang, Wenlin Yao, Kaiqiang Song, Hongming Zhang, Muhao Chen, Dong Yu


Abstract
Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics can also be interpreted via compositional operations such as sentence fusion or difference. It is unclear whether the compositional semantics of sentences can be directly reflected as compositional operations in the embedding space. To more effectively bridge the continuous embedding and discrete text spaces, we explore the plausibility of incorporating various compositional properties into the sentence embedding space that allows us to interpret embedding transformations as compositional sentence operations. We propose InterSent, an end-to-end framework for learning interpretable sentence embeddings that supports compositional sentence operations in the embedding space. Our method optimizes operator networks and a bottleneck encoder-decoder model to produce meaningful and interpretable sentence embeddings. Experimental results demonstrate that our method significantly improves the interpretability of sentence embeddings on four textual generation tasks over existing approaches while maintaining strong performance on traditional semantic similarity tasks.
Anthology ID:
2023.emnlp-main.900
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14584–14595
Language:
URL:
https://aclanthology.org/2023.emnlp-main.900
DOI:
10.18653/v1/2023.emnlp-main.900
Bibkey:
Cite (ACL):
James Y. Huang, Wenlin Yao, Kaiqiang Song, Hongming Zhang, Muhao Chen, and Dong Yu. 2023. Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14584–14595, Singapore. Association for Computational Linguistics.
Cite (Informal):
Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations (Huang et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.900.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.900.mp4