Machine Translation, it’s a question of style, innit? The case of English tag questions

Abstract : In this paper, we address the problem of generating English tag questions (TQs) (e.g. it is, isn't it?) in Machine Translation (MT). We propose a post-edition solution, formulating the problem as a multi-class classification task. We present (i) the automatic annotation of English TQs in a parallel corpus of subtitles and (ii) an approach using a series of classifiers to predict TQ forms, which we use to post-edit state-of-the-art MT outputs. Our method provides significant improvements in English TQ translation when translating from Czech, French and German, in turn improving the fluidity, naturalness, grammatical correctness and pragmatic coherence of MT output.
Type de document :
Communication dans un congrès
Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), Sep 2017, Copenhague, Denmark. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp.2497-2502, 〈http://emnlp2017.net/〉
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01588171
Contributeur : Rachel Bawden <>
Soumis le : vendredi 15 septembre 2017 - 11:24:04
Dernière modification le : jeudi 11 janvier 2018 - 06:25:47
Document(s) archivé(s) le : samedi 16 décembre 2017 - 13:27:13

Fichier

TQs.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01588171, version 1

Collections

Citation

Rachel Bawden. Machine Translation, it’s a question of style, innit? The case of English tag questions. Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), Sep 2017, Copenhague, Denmark. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp.2497-2502, 〈http://emnlp2017.net/〉. 〈hal-01588171〉

Partager

Métriques

Consultations de la notice

985

Téléchargements de fichiers

104