Quantifying Synthesis and Fusion and their Impact on Machine Translation

Abstract

Theoretical work in morphological typology offers the possibility of measuring morphological diversity on a continuous scale. However, literature in NLP typically labels a whole language with a strict type of morphology, e.g. fusional or agglutinative. In this work, we propose to reduce the theoretical rigidity of such claims, by quantifying the morphological typology at the word and segment level. We consider Payne (2017)'s approach to classify morphology using two indices: synthesis (from 1 for analytic to 3 or more for polysynthetic) and fusion (from 0 for agglutinative to 1 for fusional). For computing synthesis, we test unsupervised and supervised morphological segmentation methods for English, German and Turkish, whereas for fusion, we propose a semi-automatic method using Spanish as a case study.Then, we analyse the relationship between machine translation quality and the degree of synthesis and fusion at word (nouns and verbs for English-Turkish, and verbs in English-Spanish) and segment level (previous language pairs plus English-German in both directions). We complement the word-level analysis with human evaluation, and overall, we observe a consistent impact of both indexes on machine translation quality.

Tasks

Reproductions