Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation
Benjamin Muller, Luca Soldaini, Rik Koncel-Kedziorski, Eric Lind, Alessandro Moschitti
Abstract
Open-Domain Generative Question Answering has achieved impressive performance in English by combining document-level retrieval with answer generation. These approaches, which we refer to as GenQA, can generate complete sentences, effectively answering both factoid and non-factoid questions. In this paper, we extend to the multilingual and cross-lingual settings. For this purpose, we first introduce GenTyDiQA, an extension of the TyDiQA dataset with well-formed and complete answers for Arabic, Bengali, English, Japanese, and Russian. Based on GenTyDiQA, we design a cross-lingual generative model that produces full-sentence answers by exploiting passages written in multiple languages, including languages different from the question. Our cross-lingual generative system outperforms answer sentence selection baselines for all 5 languages and monolingual generative pipelines for three out of five languages studied.- Anthology ID:
- 2022.aacl-main.27
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Editors:
- Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 337–353
- Language:
- URL:
- https://aclanthology.org/2022.aacl-main.27
- DOI:
- Cite (ACL):
- Benjamin Muller, Luca Soldaini, Rik Koncel-Kedziorski, Eric Lind, and Alessandro Moschitti. 2022. Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 337–353, Online only. Association for Computational Linguistics.
- Cite (Informal):
- Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation (Muller et al., AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2022.aacl-main.27.pdf