Mitigating Semantic Leakage in Cross-lingual Embeddings via Orthogonality Constraint

Dayeon Ki, Cheonbok Park, Hyunjoong Kim


Abstract
Accurately aligning contextual representations in cross-lingual sentence embeddings is key for effective parallel data mining. A common strategy for achieving this alignment involves disentangling semantics and language in sentence embeddings derived from multilingual pre-trained models. However, we discover that current disentangled representation learning methods suffer from semantic leakage—a term we introduce to describe when a substantial amount of language-specific information is unintentionally leaked into semantic representations. This hinders the effective disentanglement of semantic and language representations, making it difficult to retrieve embeddings that distinctively represent the meaning of the sentence. To address this challenge, we propose a novel training objective, ORthogonAlity Constraint LEarning (ORACLE), tailored to enforce orthogonality between semantic and language embeddings. ORACLE builds upon two components: intra-class clustering and inter-class separation. Through experiments on cross-lingual retrieval and semantic textual similarity tasks, we demonstrate that training with the ORACLE objective effectively reduces semantic leakage and enhances semantic alignment within the embedding space.
Anthology ID:
2024.repl4nlp-1.19
Volume:
Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Chen Zhao, Marius Mosbach, Pepa Atanasova, Seraphina Goldfarb-Tarrent, Peter Hase, Arian Hosseini, Maha Elbayad, Sandro Pezzelle, Maximilian Mozes
Venues:
RepL4NLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
256–273
Language:
URL:
https://aclanthology.org/2024.repl4nlp-1.19
DOI:
Bibkey:
Cite (ACL):
Dayeon Ki, Cheonbok Park, and Hyunjoong Kim. 2024. Mitigating Semantic Leakage in Cross-lingual Embeddings via Orthogonality Constraint. In Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024), pages 256–273, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Mitigating Semantic Leakage in Cross-lingual Embeddings via Orthogonality Constraint (Ki et al., RepL4NLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.repl4nlp-1.19.pdf