Fine-grained evaluation of German-English Machine Translation based on a Test Suite

TL;DR

This paper conducts a detailed analysis of 16 German-English machine translation systems using a comprehensive, linguistically-motivated test suite to identify strengths and weaknesses across various linguistic phenomena.

Contribution

It introduces a manually created test suite covering 106 linguistic phenomena, enabling fine-grained evaluation of MT systems' linguistic capabilities.

Findings

Identifies specific linguistic phenomena where MT systems perform poorly.

Provides a comparative analysis of 16 MT systems across multiple linguistic categories.

Highlights areas for improvement in current machine translation models.

Abstract

We present an analysis of 16 state-of-the-art MT systems on German-English based on a linguistically-motivated test suite. The test suite has been devised manually by a team of language professionals in order to cover a broad variety of linguistic phenomena that MT often fails to translate properly. It contains 5,000 test sentences covering 106 linguistic phenomena in 14 categories, with an increased focus on verb tenses, aspects and moods. The MT outputs are evaluated in a semi-automatic way through regular expressions that focus only on the part of the sentence that is relevant to each phenomenon. Through our analysis, we are able to compare systems based on their performance on these categories. Additionally, we reveal strengths and weaknesses of particular systems and we identify grammatical phenomena where the overall performance of MT is relatively low.