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

13 pages•Published: November 28, 2016

Mario Crespo Miguel and Marta Sanchez-Saus Laserna

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.

Keyphrases: aligned corpora, evaluation, machine translation, statistical analysis

In: Antonio Moreno Ortiz and Chantal Pérez-Hernández (editors). CILC2016. 8th International Conference on Corpus Linguistics, vol 1, pages 58-70.

Links:	https://easychair.org/publications/paper/LM4
	https://doi.org/10.29007/r819

BibTeX entry

@inproceedings{CILC2016:Graded_Acceptance_Corpus_Based,
  author    = {Mario Crespo Miguel and Marta Sanchez-Saus Laserna},
  title     = {Graded Acceptance in Corpus-Based English-to-Spanish Machine Translation Evaluation},
  booktitle = {CILC2016. 8th International Conference on Corpus Linguistics},
  editor    = {Antonio Moreno Ortiz and Chantal Pérez-Hernández},
  series    = {EPiC Series in Language and Linguistics},
  volume    = {1},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-5283},
  url       = {/publications/paper/LM4},
  doi       = {10.29007/r819},
  pages     = {58-70},
  year      = {2016}}

Download PDF Open PDF in browser