RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction

TL;DR

RAPO introduces a personalized, ranking-oriented approach for bilingual lexicon induction that improves translation accuracy by learning individual mapping functions for each word, outperforming existing methods across diverse language resources.

Contribution

The paper presents RAPO, a novel model that learns personalized mapping functions for each word, enhancing bilingual lexicon induction by leveraging word-specific and cross-lingual features.

Findings

Outperforms existing methods on public datasets.

Effective for both rich-resource and low-resource languages.

Demonstrates superior discriminative capability in translation ranking.

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}.