Skip to content
conftrace_
2020 EMNLP EMNLP 2020

Improving Bilingual Lexicon Induction for Low Frequency Words

AbstractThis 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.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

More from EMNLP 2020

All EMNLP 2020 papers →