RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction
Year: 2022
Type: other
Abstract: Bilingual lexicon induction induces the word translations by aligning independently trained word embeddings in two languages. Existing approaches generally focus on minimizing the distances between words in the aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. In addition, the mapping function is globally shared by all words, whose performance might be hindered by the deviations in the distributions of different languages. In this work, we propose a novel ranking-oriented induction model RAPO to learn personalized mapping function for each word. RAPO is capable of enjoying the merits from the unique characteristics of a single word and the cross-language isomorphism simultaneously. Extensive experimental results on public datasets including both rich-resource and low-resource languages demonstrate the superiority of our proposal. Our code is publicly available in \url{https://github.com/Jlfj345wf/RAPO}.
Source: Underline Science Inc.
DOI: 10.48448/dbt8-x891
Authors: Association for Computational Linguistics 2022, Deng, Weiwei, Han, Xiao, Hu, Xinyue, Huang, Haizhen, Li, Chaozhuo, Ren, Shuo, Tian, Zhoujin, Wen, Zengxuan, Xie, Xing, Zhang, Qi, Zuo, Zhiqiang
Institutions: Microsoft (United States), Microsoft Research Asia (China)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6910612937
