M2QA: Multi-domain Multilingual Question Answering

Leon Engländer, Hannah Sterz, Clifton Poth, Jonas Pfeiffer, Ilia Kuznetsov, Iryna Gurevych


Abstract
Generalization and robustness to input variation are core desiderata of machine learning research. Language varies along several axes, most importantly, language instance (e.g. French) and domain (e.g. news). While adapting NLP models to new languages within a single domain, or to new domains within a single language, is widely studied, research in joint adaptation is hampered by the lack of evaluation datasets. This prevents the transfer of NLP systems from well-resourced languages and domains to non-dominant language-domain combinations. To address this gap, we introduce M2QA, a multi-domain multilingual question answering benchmark.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. We use M2QA to explore cross-lingual cross-domain performance of fine-tuned models and state-of-the-art LLMs and investigate modular approaches to domain and language adaptation.We witness **1)** considerable performance _variations_ across domain-language combinations within model classes and **2)** considerable performance _drops_ between source and target language-domain combinations across all model sizes. We demonstrate that M2QA is far from solved, and new methods to effectively transfer both linguistic and domain-specific information are necessary.
Anthology ID:
2024.findings-emnlp.365
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6283–6305
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.365
DOI:
Bibkey:
Cite (ACL):
Leon Engländer, Hannah Sterz, Clifton Poth, Jonas Pfeiffer, Ilia Kuznetsov, and Iryna Gurevych. 2024. M2QA: Multi-domain Multilingual Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6283–6305, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
M2QA: Multi-domain Multilingual Question Answering (Engländer et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.365.pdf
Software:
 2024.findings-emnlp.365.software.zip
Data:
 2024.findings-emnlp.365.data.zip