Pivot Through English: Reliably Answering Multilingual Questions without Document Retrieval

Ivan Montero, Shayne Longpre, Ni Lao, Andrew Frank, Christopher DuBois


Abstract
Existing methods for open-retrieval question answering in lower resource languages (LRLs) lag significantly behind English. They not only suffer from the shortcomings of non-English document retrieval, but are reliant on language-specific supervision for either the task or translation. We formulate a task setup more realistic to available resources, that circumvents document retrieval to reliably transfer knowledge from English to lower resource languages. Assuming a strong English question answering model or database, we compare and analyze methods that pivot through English: to map foreign queries to English and then English answers back to target language answers. Within this task setup we propose Reranked Multilingual Maximal Inner Product Search (RM-MIPS), akin to semantic similarity retrieval over the English training set with reranking, which outperforms the strongest baselines by 2.7% on XQuAD and 6.2% on MKQA. Analysis demonstrates the particular efficacy of this strategy over state-of-the-art alternatives in challenging settings: low-resource languages, with extensive distractor data and query distribution misalignment. Circumventing retrieval, our analysis shows this approach offers rapid answer generation to many other languages off-the-shelf, without necessitating additional training data in the target language.
Anthology ID:
2022.mia-1.3
Volume:
Proceedings of the Workshop on Multilingual Information Access (MIA)
Month:
July
Year:
2022
Address:
Seattle, USA
Editors:
Akari Asai, Eunsol Choi, Jonathan H. Clark, Junjie Hu, Chia-Hsuan Lee, Jungo Kasai, Shayne Longpre, Ikuya Yamada, Rui Zhang
Venue:
MIA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16–28
Language:
URL:
https://aclanthology.org/2022.mia-1.3
DOI:
10.18653/v1/2022.mia-1.3
Bibkey:
Cite (ACL):
Ivan Montero, Shayne Longpre, Ni Lao, Andrew Frank, and Christopher DuBois. 2022. Pivot Through English: Reliably Answering Multilingual Questions without Document Retrieval. In Proceedings of the Workshop on Multilingual Information Access (MIA), pages 16–28, Seattle, USA. Association for Computational Linguistics.
Cite (Informal):
Pivot Through English: Reliably Answering Multilingual Questions without Document Retrieval (Montero et al., MIA 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.mia-1.3.pdf
Data
MKQANatural QuestionsPAWSPAWS-XSQuADXQuAD