Abstract
Semantics of a sentence is defined with much less ambiguity than semantics of a single word, and we assume that it should be better preserved by translation to another language. If multilingual sentence embeddings intend to represent sentence semantics, then the similarity between embeddings of any two sentences must be invariant with respect to translation. Based on this suggestion, we consider a simple linear cross-lingual mapping as a possible improvement of the multilingual embeddings. We also consider deviation from orthogonality conditions as a measure of deficiency of the embeddings.- Anthology ID:
- 2024.findings-acl.486
- Volume:
- Findings of the Association for Computational Linguistics ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand and virtual meeting
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8163–8171
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.486
- DOI:
- Cite (ACL):
- Oleg Vasilyev, Fumika Isono, and John Bohannon. 2024. Linear Cross-Lingual Mapping of Sentence Embeddings. In Findings of the Association for Computational Linguistics ACL 2024, pages 8163–8171, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- Linear Cross-Lingual Mapping of Sentence Embeddings (Vasilyev et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.486.pdf