M2QA: A Multi-domain Multilingual Question Answering Benchmark Dataset

M2QA (Multi-domain Multilingual Question Answering) is an extractive question answering benchmark for evaluating joint language and domain transfer. M2QA includes 13,500 SQuAD 2.0-style question-answer instances in German, Turkish, and Chinese for the domains of product reviews, news, and creative writing.

Identifier
Source https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/4601
Related Identifier IsSupplementTo https://doi.org/10.18653/v1/2024.findings-emnlp.365
Metadata Access https://tudatalib.ulb.tu-darmstadt.de/oai/openairedata?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:tudatalib.ulb.tu-darmstadt.de:tudatalib/4601
Provenance
Creator Engländer, Leon; Sterz, Hannah; Poth, Clifton A; Pfeiffer, Jonas; Kuznetsov, Ilia; Gurevych, Iryna
Publisher TU Darmstadt
Contributor European Commission; TU Darmstadt
Publication Year 2024
Funding Reference European Commission info:eu-repo/grantAgreement/EC/HE/101054961
Rights CC-BY-ND 4.0; info:eu-repo/semantics/openAccess
OpenAccess true
Contact https://tudatalib.ulb.tu-darmstadt.de/page/contact
Representation
Resource Type Dataset
Format application/zip
Version v. 1.0
Discipline Other