DiaBLa: a corpus of bilingual spontaneous written dialogues for machine translation

Autor: Eric Bilinski, Sophie Rosset, Thomas Lavergne, Rachel Bawden
Přispěvatelé: School of Informatics [Edimbourg], University of Edinburgh, Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), University of Paris Sud (UPSUD)
Rok vydání: 2020
Předmět:
FOS: Computer and information sciences
Linguistics and Language
French
Machine translation
Computer science
02 engineering and technology
Library and Information Sciences
Corpus
computer.software_genre
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Language and Linguistics
Education
English
0202 electrical engineering
electronic engineering
information engineering
Dialogue
Evaluation of machine translation
Evaluation
060201 languages & linguistics
Computer Science - Computation and Language
business.industry
Context
06 humanities and the arts
Bilingual conversation
Test set
0602 languages and literature
020201 artificial intelligence & image processing
Artificial intelligence
Computational linguistics
business
Computation and Language (cs.CL)
computer
Natural language processing
Dataset
Zdroj: Language Resources and Evaluation
Language Resources and Evaluation, Springer Verlag, 2020, ⟨10.1007/s10579-020-09514-4⟩
ISSN: 1574-0218
1574-020X
DOI: 10.1007/s10579-020-09514-4
Popis: We present a new English–French dataset for the evaluation of Machine Translation (MT) for informal, written bilingual dialogue. The test set contains 144 spontaneous dialogues (5700+ sentences) between native English and French speakers, mediated by one of two neural MT systems in a range of role-play settings. The dialogues are accompanied by fine-grained sentence-level judgments of MT quality, produced by the dialogue participants themselves, as well as by manually normalised versions and reference translations produceda posteriori. The motivation for the corpus is twofold: to provide (i) a unique resource for evaluating MT models, and (ii) a corpus for the analysis of MT-mediated communication. We provide an initial analysis of the corpus to confirm that the participants’ judgments reveal perceptible differences in MT quality between the two MT systems used.
Databáze: OpenAIRE
Externí odkaz: