The Role of Corpus Pattern Analysis in Machine Translation Evaluation

Abstract

This paper takes a preliminary look at the relation between verb pattern matches in the Pattern Dictionary of English Verbs (PDEV) and translation quality through a qualitative analysis of human-ranked sentences from 5 different machine translation systems. The purpose of the analysis is not only to determine whether verbs in the automatic translations and their immediate contexts match any pre-existing semanto-syntactic pattern in PDEV, but also to establish links between hypothesis sentences and the verbs in the reference translation. It attempts to answer the question of whether or not the semantic and syntactic information captured by Corpus Pattern Analysis (CPA) can indicate whether a sentence is a “good” translation. Two human annotators manually identified the occurrence of patterns in 50 translations and indicated whether these patterns match any identified pattern in the corresponding reference translation. Results indicate that CPA can be used to distinguish between well and ill-formed sentences.