A multingual retrieval shared task is running again this year at TREC
2024. The NeuCLIR (i.e., neural CLIR) track contains news document
collections in Chinese, Farsi, and Russian, and support subtasks in:
* cross-lingual search: search document collections from various languages
* multlingual search: produce a unified ranked list of relevant documents
across the three collections
* report generation: produce an multi-paragraph English-language
summary based on relevant information found in the source documents
* technical document CLIR: searching in a collection of Chinese technical
abstracts
Information about the track, including task guidelines is available:
https://neuclir.github.io/2024
To participate in the track advance registration for TREC 2024 is required:
https://trec.nist.gov/pubs/call2024.html
Best,
- Paul McNamee
_______________________________________________
Corpora mailing list -- [email protected]
https://list.elra.info/mailman3/postorius/lists/corpora.list.elra.info/
To unsubscribe send an email to [email protected]
