MTEB logo MTEB
semantic-similarity text

DiaBlaBitextMining

Cite this task

@article{bawden2021diabla,
  author = {Bawden, Rachel and Bilinski, Eric and Lavergne, Thomas and Rosset, Sophie},
  journal = {Language Resources and Evaluation},
  number = {3},
  pages = {635--660},
  publisher = {Springer},
  title = {DiaBLa: a corpus of bilingual spontaneous written dialogues for machine translation},
  volume = {55},
  year = {2021},
}

English-French Parallel Corpus. DiaBLa is an English-French dataset for the evaluation of Machine Translation (MT) for informal, written bilingual dialogue.

Domains: SocialWritten
Languages: EnglishFrench
Task type
BitextMining
Main metric
f1
License
cc-by-nc-sa-4.0
Dates
2016-01-01 → 2017-12-31
Annotations
human-annotated
Sample creation
created
Models scored …
Dataset preview mteb/DiaBlaBitextMining Open on HuggingFace →

Model scores

Loading…