Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph

Yucheng Zhou, Xiubo Geng, Tao Shen, Wenqiang Zhang, Daxin Jiang


Abstract
Multilingual question answering over knowledge graph (KGQA) aims to derive answers from a knowledge graph (KG) for questions in multiple languages. To be widely applicable, we focus on its zero-shot transfer setting. That is, we can only access training data in a high-resource language, while need to answer multilingual questions without any labeled data in target languages. A straightforward approach is resorting to pre-trained multilingual models (e.g., mBERT) for cross-lingual transfer, but there is a still significant gap of KGQA performance between source and target languages. In this paper, we exploit unsupervised bilingual lexicon induction (BLI) to map training questions in source language into those in target language as augmented training data, which circumvents language inconsistency between training and inference. Furthermore, we propose an adversarial learning strategy to alleviate syntax-disorder of the augmented data, making the model incline to both language- and syntax-independence. Consequently, our model narrows the gap in zero-shot cross-lingual transfer. Experiments on two multilingual KGQA datasets with 11 zero-resource languages verify its effectiveness.
Anthology ID:
2021.naacl-main.465
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5822–5834
Language:
URL:
https://aclanthology.org/2021.naacl-main.465
DOI:
10.18653/v1/2021.naacl-main.465
Bibkey:
Cite (ACL):
Yucheng Zhou, Xiubo Geng, Tao Shen, Wenqiang Zhang, and Daxin Jiang. 2021. Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5822–5834, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph (Zhou et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.465.pdf
Video:
 https://aclanthology.org/2021.naacl-main.465.mp4
Data
DBpedia