Leveraging Entity Linking and Related Language Projection to Improve Name Transliteration

Abstract

Traditional name transliteration methods largely ignore source context information and inter-dependency among entities for entity disambiguation. We propose a novel approach to leverage state-of-the-art Entity Linking (EL) techniques to automatically correct name transliteration results, using collective inference from source contexts and additional evidence from knowledge base. Experiments on transliterating names from seven languages to English demonstrate that our approach achieves 2.6% to 15.7% absolute gain over the baseline model, and significantly advances state-of-the-art. When contextual information exists, our approach can achieve further gains (24.2%) by collectively transliterating and disambiguating multiple related entities. We also prove that combining Entity Linking and projecting resources from related languages obtained comparable performance as the method using the same amount of training pairs in the original languages without Entity Linking. 1

Transliteration for Cross-Lingual Morphological Inflection

“…Notably, even though romanization is fairly well-studied and are easily attainable through tools like URoman, the opposite direction is fairly understudied. Most of the related work has focused on either to-English transliteration specifically (Lin et al, 2016;Durrani et al, 2014) or on named entity transliteration (Kundu et al, 2018;Grundkiewicz and Heafield, 2018). Even then, the state-of-the-art results on the recent NEWS named entity transliteration task (Chen et al, 2018) ranged from 10% to 80% in terms of accuracy across several scripts.…”

Bootstrapping Transliteration with Constrained Discovery for Low-Resource Languages

“…Our constrained inference strategy is much simpler, requiring only a name dictionary N . We experimentally show that our approach outperforms that of Lin et al (2016).…”

Learning Morphosyntactic Analyzers from the Bible via Iterative Annotation Projection across 26 Languages

“…In the area of contraint-based discovery, our methodology most closely resembles the constrained discovery systems of Lin et al (2016) and particularly Upadhyay et al (2018). Starting from a high-quality seed, a learning algorithm generalizes observed patterns, iteratively increasing the seed data with confident examples, while discarding examples that fail to pass certain heuristics.…”