Effective Architectures for Low Resource Multilingual Named Entity Transliteration
Molly A. Moran, Constantine Lignos · 2020
In this paper, we evaluate LSTM, biLSTM, GRU, and Transformer architectures for the task of name transliteration in a many-to-one multilingual paradigm, transliterating from 590 languages to English.We experiment with different encoder-decoder combinations and evaluate them using accuracy, character error rate, and an F-measure based on longest continuous subsequences.We find that using a Transformer for the encoder and decoder performs best, improving accuracy by over 4 points compared to previous work.We explore whether manipulating the source text by adding macrolanguage flag tokens or preromanizing source strings can improve performance and find that neither manipulation has a positive effect.Finally, we analyze performance differences between the LSTM and Transformer encoders when using a Transformer decoder and find that the Transformer encoder is better able to handle insertions and substitutions when transliterating.