Shared Task: Biomedical Translation Task
Task description
This task aims to evaluate systems on the translation of documents from the biomedical domain.
The test data will consist of biomedical abstracts and it will address the following language pairs:
-
English-Chinese and Chinese-English (en/zh, zh/en) Unfortunately, no zh/en test sets this year.
- English-French and French-English (en/fr, fr/en)
- English-German and German-English (en/de, de/en)
- English-Italian and Italian-English (en/it, it/en)
- English-Portuguese and Portuguese-English (en/pt, pt/en)
- English-Russian and Russian-English (en/ru, ru/en)
- English-Spanish and Spanish-English (en/es, es/en)
Data
ATTENTION!!
We ask the participants to not download the Medline database by themselves in order to retrieve training data.
Submissions that are derived from a model that was trained on the whole PubMed will be not considered in the evaluation.
Participants can rely on training (and development) data from various sources, for instance:
- The Biomedical Translation repository includes links to
parallel corpora of scientific publications (en/pt, en/es, en/fr, en/de, en/zh, en/it, en/ru), among others
- The UFAL Medical Corpus (formerly HimLCorpus) includes
medical text from various sources for many language pairs (en/es, en/de, en/fr, en/ro)
HimL test sets can be used as the development sets for some language pairs (en/es, en/de, en/fr, en/ro)
- The Khresmoi development data can be used for some language pairs (en/es, en/de, en/fr).
- The UNCorpus contains training data for some languages (en/es, en/fr, en/zh)
- The MeSpEn corpus contains many parallel documents of en/es
- The Scielo full text corpus for en, es and pt
- The Brazilian Thesis and Dissertations for en/pt
Participants are also free to use out-of-domain data.
Evaluation
Evaluation will be carried out both automatically and manually.
Automatic evaluation will make use of standard machine translation metrics, such as BLEU.
Native speakers of each of the languages will manually check the quality of the translation for a small sample of the submissions.
If necessary, we also expect participants to support us in the manual evaluation (accordingly to the number of submissions).
We plan to release test sets for the following language pairs and sources:
- Scientific abstracts:
Chinese/English (both directions) Unfortunately, no zh/en test sets this year.
- French/English (both directions)
- German/English (both directions)
- Italian/English (both directions)
- Portuguese/English (both directions)
- Russian/English (both directions)
- Spanish/English (both directions)
Scientific abstracts:
For the test set of Medline abstracts, the format will be plain text files.
The format will be the following:
DOC_ID SENT_ID SENTENCE_TEXT
The three values are separated by a TAB character:
- DOC_ID: sequential one, e.g. doc1, doc8, not the original PMID in Medline
- SENT_ID: a sequential number from 1 to n
- SENTENCE_TEXT: the sentence text to be translated by the participants
doc1 1 sentence_1
doc2 2 sentence_2
doc2 3 sentence_3
doc2 4 sentence_4
doc2 5 sentence_5
...
doc2 n sentence_n
doc4 1 sentence_1
doc4 2 sentence_2
...
The format for the submission will be the same, such as in the example below.
The participants should follow the same order of the sentences as in the original test set file.
doc1 1 translated_sentence_1
doc2 2 translated_sentence_2
doc2 3 translated_sentence_3
doc2 4 translated_sentence_4
doc2 5 translated_sentence_5
...
doc2 n translated_sentence_n
doc4 1 translated_sentence_1
doc4 2 translated_sentence_2
...
Submission Requirements
Please notice that, following general WMT policy explicitly enforced in other tasks, we will release all participants'
submissions after this year's edition of the task to promote further studies.
Please register your team using this form.
You will receive a mail with the confirmation of your registration.
The link for submission site will be informed in this mail.
Please register your team as soon as possible.
The Medline test files are available in the WMT'23 biomedical task Google Drive folder.
The format for the submission files should include the original test file name preceded by the team identifier
(as registered in the form above) and the run number, following this example for the abstracts:
- The submission file for run 1 of the "ABC" team for the Medline scientific abstracts from English into Spanish should be called
"ABC_run1_medline_en2es_es.txt".
- The submission file for run 3 of the "ABC" team for the Medline scientific abstracts from Spanish into English should be called
"ABC_run3_medline_es2en_en.txt".
Each team will be allowed to submit up to 3 runs per test set.
Please notice that the submission form will include questions about details of your methods, please inform as much details as possible, this is important for us.
Results
Initial results for the biomedical task are available here.
Important dates
Release of test data | July 13th, 2023 |
Results submission deadline | July 20th, 2023 July 25th, 2023 |
Paper submission deadline | TBA September, 2023 |
Paper notification | TBA October, 2023 |
Camera-ready version due | 20th October, 2023 |
Conference EMNLP | 6-7 December, 2023 |
All deadlines are in AoE (Anywhere on Earth).
Organisers
Rachel Bawden (University of Edinburgh, UK)
Giorgio Maria Di Nunzio (University of Padua, Italy)
Cristian Grozea (Fraunhofer Institute, Germany)
Antonio Jimeno Yepes (University of Melbourne, Australia)
Aurélie Névéol (Université Paris Saclay, CNRS, LISN, France)
Mariana Neves (German Federal Institute for Risk Assessment, Germany)
Roland Roller (DFKI, Germany)
Amy Siu (Beuth University of Applied Sciences, Germany)
Philippe Thomas (DFKI, Germany)
Federica Vezzani (University of Padua, Italy)
Maika Vicente Navarro, Maika Spanish Translator, Melbourne, Australia
Dina Wiemann (Novartis, Switzerland)
Lana Yeganova (NCBI/NLM/NIH, USA)
Please contact us in the mail wmtbiomedical@gmail.com.
Please join our discussion forum.