How do lexical semantics affect translation? An empirical study
This work addresses translation challenges for low-resource language pairs, but it is incremental as it builds on existing NMT methods with empirical analysis.
The study investigated how lexical similarity and word ordering between source and target languages affect neural machine translation performance, finding that greater similarity to English improves translation, and part-of-speech tagging benefits Transformer models more for dissimilar languages.
Neural machine translation (NMT) systems aim to map text from one language into another. While there are a wide variety of applications of NMT, one of the most important is translation of natural language. A distinguishing factor of natural language is that words are typically ordered according to the rules of the grammar of a given language. Although many advances have been made in developing NMT systems for translating natural language, little research has been done on understanding how the word ordering of and lexical similarity between the source and target language affect translation performance. Here, we investigate these relationships on a variety of low-resource language pairs from the OpenSubtitles2016 database, where the source language is English, and find that the more similar the target language is to English, the greater the translation performance. In addition, we study the impact of providing NMT models with part of speech of words (POS) in the English sequence and find that, for Transformer-based models, the more dissimilar the target language is from English, the greater the benefit provided by POS.