String Transduction with Target Language Models and Insertion Handling

Abstract

Many character-level tasks can be framed as sequence-to-sequence transduction, where the target is a word from a natural language. We show that leveraging target language models derived from unannotated target corpora, combined with a precise alignment of the training data, yields state-of-the art results on cognate projection, inflection generation, and phoneme-to-grapheme conversion.

8 pages + 1 page Appendix, 4 figures and 8 tables, plus an additional 1 figure and 2 tables in appendix; to appear at SIGMORPHON 2018, October, 2018