Graded Acceptance in Corpus-Based English-to-Spanish Machine Translation Evaluation

Abstract

Traditionally, texts provided by machine translation have been evaluated with a binary criterion: right or wrong. However, in certain cases it is difficult to provide a clear-cut division between fully acceptable and fully unacceptable texts. In this paper we have selected group of different bilingual, human-translated English-to-Spanish pairs of sentences from parallel corpora (Linguee) and a group of machine translated texts with problematic linguistic phenomena in English-to-Spanish translation: polysemy, semantic equivalents, passive, anaphora, etc. We presented the translations to a group of native speakers that evaluated them in different levels of acceptability. Results show the degree of applicability of this approach.