Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations
This work addresses the problem of NLP generalization for low-resourced languages, offering a method that is incremental but provides specific gains in tasks like Named Entity Recognition and Machine Translation.
The paper tackles the challenge of adapting word embeddings to low-resourced languages by using morphological and phonological subword representations, achieving improvements such as +15.2 NER F1 for Uyghur and +9.7 F1 for Bengali without requiring parallel corpora or bilingual dictionaries.
Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging. We present two approaches for improving generalization to low-resourced languages by adapting continuous word representations using linguistically motivated subword units: phonemes, morphemes and graphemes. Our method requires neither parallel corpora nor bilingual dictionaries and provides a significant gain in performance over previous methods relying on these resources. We demonstrate the effectiveness of our approaches on Named Entity Recognition for four languages, namely Uyghur, Turkish, Bengali and Hindi, of which Uyghur and Bengali are low resource languages, and also perform experiments on Machine Translation. Exploiting subwords with transfer learning gives us a boost of +15.2 NER F1 for Uyghur and +9.7 F1 for Bengali. We also show improvements in the monolingual setting where we achieve (avg.) +3 F1 and (avg.) +1.35 BLEU.