Quantifying Synthesis and Fusion and their Impact on Machine Translation

TL;DR

This paper introduces a method to quantify morphological diversity in languages using synthesis and fusion indices, and analyzes their impact on machine translation quality across multiple language pairs.

Contribution

It proposes a novel approach to measure morphological typology at word and segment levels and examines their influence on machine translation performance.

Findings

Both synthesis and fusion indices significantly affect translation quality.

Unsupervised segmentation methods are effective for measuring synthesis.

Human evaluation supports the impact of morphological typology on MT quality.

Abstract

Theoretical work in morphological typology offers the possibility of measuring morphological diversity on a continuous scale. However, literature in Natural Language Processing (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 rigidity of such claims, by quantifying morphological typology at the word and segment level. We consider Payne (2017)'s approach to classify morphology using two indices: synthesis (e.g. analytic to polysynthetic) and fusion (agglutinative to 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.