Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

Christian Hardmeier, Qatar Computing Institute, Sara Stymne, Jörg Tiedemann, Yannick Versley, Mauro Cettolo

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

Abstrakti

We describe the design, the evaluation setup, and the results of the DiscoMT 2015 shared task, which included two subtasks, relevant to both the machine translation (MT) and the discourse communities: (i) pronoun-focused translation, a practical MT task, and (ii) cross-lingual pronoun prediction, a classification task that requires no specific MT expertise and is interesting as a machine learning task in its own right. We focused on the English–French language pair, for which MT output is generally of high quality, but has visible issues with pronoun translation due
to differences in the pronoun systems of the two languages. Six groups participated in the pronoun-focused translation task and eight groups in the cross-lingual pronoun prediction task
Alkuperäiskielimuu / ei tiedossa
OtsikkoProceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT),
Sivumäärä16
KustantajaThe Association for Computational Linguistics
Julkaisupäivä1 syysk. 2015
Sivut1-16
ISBN (painettu)978-1-94163-32-7
TilaJulkaistu - 1 syysk. 2015
Julkaistu ulkoisestiKyllä
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaWorkshop on Discourse in Machine Translation (DiscoMT), - Lisbon, Portugali
Kesto: 17 syysk. 201517 syysk. 2015
Konferenssinumero: 2

Tieteenalat

  • 6121 Kielitieteet

Siteeraa tätä