Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages
This addresses the challenge of supporting low-resource languages in NLP, which is incremental as it builds on related-language methods but extends them via chains and anchoring.
The paper tackles the problem of poor cross-lingual word representations for very low-resource languages by proposing a language chain-based approach to build multilingual word embeddings, showing improved performance in bilingual lexicon induction for 4 very low-resource and 4 moderately low-resource target languages.
Very low-resource languages, having only a few million tokens worth of data, are not well-supported by multilingual NLP approaches due to poor quality cross-lingual word representations. Recent work showed that good cross-lingual performance can be achieved if a source language is related to the low-resource target language. However, not all language pairs are related. In this paper, we propose to build multilingual word embeddings (MWEs) via a novel language chain-based approach, that incorporates intermediate related languages to bridge the gap between the distant source and target. We build MWEs one language at a time by starting from the resource rich source and sequentially adding each language in the chain till we reach the target. We extend a semi-joint bilingual approach to multiple languages in order to eliminate the main weakness of previous works, i.e., independently trained monolingual embeddings, by anchoring the target language around the multilingual space. We evaluate our method on bilingual lexicon induction for 4 language families, involving 4 very low-resource (<5M tokens) and 4 moderately low-resource (<50M) target languages, showing improved performance in both categories. Additionally, our analysis reveals the importance of good quality embeddings for intermediate languages as well as the importance of leveraging anchor points from all languages in the multilingual space.