Enhancing Bilingual Lexicon Induction via Bi-directional Translation Pair Retrieving
Qiuyu Ding, Hailong Cao, Tiejun Zhao
Abstract
Most Bilingual Lexicon Induction (BLI) methods retrieve word translation pairs by finding the closest target word for a given source word based on cross-lingual word embeddings (WEs). However, we find that solely retrieving translation from the source-to-target perspective leads to some false positive translation pairs, which significantly harm the precision of BLI. To address this problem, we propose a novel and effective method to improve translation pair retrieval in cross-lingual WEs. Specifically, we consider both source-side and target-side perspectives throughout the retrieval process to alleviate false positive word pairings that emanate from a single perspective. On a benchmark dataset of BLI, our proposed method achieves competitive performance compared to existing state-of-the-art (SOTA) methods. It demonstrates effectiveness and robustness across six experimental languages, including similar language pairs and distant language pairs, under both supervised and unsupervised settings.
BibTeX
@article{Ding_Cao_Zhao_2024, title={Enhancing Bilingual Lexicon Induction via Bi-directional Translation Pair Retrieving}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/29744}, DOI={10.1609/aaai.v38i16.29744}, abstractNote={Most Bilingual Lexicon Induction (BLI) methods retrieve word translation pairs by finding the closest target word for a given source word based on cross-lingual word embeddings (WEs). However, we find that solely retrieving translation from the source-to-target perspective leads to some false positive translation pairs, which significantly harm the precision of BLI. To address this problem, we propose a novel and effective method to improve translation pair retrieval in cross-lingual WEs. Specifically, we consider both source-side and target-side perspectives throughout the retrieval process to alleviate false positive word pairings that emanate from a single perspective. On a benchmark dataset of BLI, our proposed method achieves competitive performance compared to existing state-of-the-art (SOTA) methods. It demonstrates effectiveness and robustness across six experimental languages, including similar language pairs and distant language pairs, under both supervised and unsupervised settings.}, number={16}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Ding, Qiuyu and Cao, Hailong and Zhao, Tiejun}, year={2024}, month={Mar.}, pages={17898-17906} }