Improving Bilingual Lexicon Induction for Low Frequency Words
2020-11-01EMNLP 2020Unverified0· sign in to hype
Jiaji Huang, Xingyu Cai, Kenneth Church
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
This paper designs a Monolingual Lexicon Induction task and observes that two factors accompany the degraded accuracy of bilingual lexicon induction for rare words. First, a diminishing margin between similarities in low frequency regime, and secondly, exacerbated hubness at low frequency. Based on the observation, we further propose two methods to address these two factors, respectively. The larger issue is hubness. Addressing that improves induction accuracy significantly, especially for low-frequency words.