Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Robust cross-lingual knowledge base question answering via knowledge distillation

Robust cross-lingual knowledge base question answering via knowledge distillation Previous knowledge base question answering (KBQA) models only consider the monolingual scenario and cannot be directly extended to the cross-lingual scenario, in which the language of questions and that of knowledge base (KB) are different. Although a machine translation (MT) model can bridge the gap through translating questions to the language of KB, the noises of translated questions could accumulate and further sharply impair the final performance. Therefore, the authors propose a method to improve the robustness of KBQA models in the cross-lingual scenario.Design/methodology/approachThe authors propose a knowledge distillation-based robustness enhancement (KDRE) method. Specifically, first a monolingual model (teacher) is trained by ground truth (GT) data. Then to imitate the practical noises, a noise-generating model is designed to inject two types of noise into questions: general noise and translation-aware noise. Finally, the noisy questions are input into the student model. Meanwhile, the student model is jointly trained by GT data and distilled data, which are derived from the teacher when feeding GT questions.FindingsThe experimental results demonstrate that KDRE can improve the performance of models in the cross-lingual scenario. The performance of each module in KBQA model is improved by KDRE. The knowledge distillation (KD) and noise-generating model in the method can complementarily boost the robustness of models.Originality/valueThe authors first extend KBQA models from monolingual to cross-lingual scenario. Also, the authors first implement KD for KBQA to develop robust cross-lingual models. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Data Technologies and Applications Emerald Publishing

Robust cross-lingual knowledge base question answering via knowledge distillation

Wang, Shaofei; Dang, Depeng
Data Technologies and Applications , Volume 55 (5): 21 – Oct 11, 2021
Download PDF
21 pages

Loading next page...
 
/lp/emerald-publishing/robust-cross-lingual-knowledge-base-question-answering-via-knowledge-Qf5izdKuMo

References (31)

Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
2514-9288
DOI
10.1108/dta-12-2020-0312
Publisher site
See Article on Publisher Site

Abstract

Previous knowledge base question answering (KBQA) models only consider the monolingual scenario and cannot be directly extended to the cross-lingual scenario, in which the language of questions and that of knowledge base (KB) are different. Although a machine translation (MT) model can bridge the gap through translating questions to the language of KB, the noises of translated questions could accumulate and further sharply impair the final performance. Therefore, the authors propose a method to improve the robustness of KBQA models in the cross-lingual scenario.Design/methodology/approachThe authors propose a knowledge distillation-based robustness enhancement (KDRE) method. Specifically, first a monolingual model (teacher) is trained by ground truth (GT) data. Then to imitate the practical noises, a noise-generating model is designed to inject two types of noise into questions: general noise and translation-aware noise. Finally, the noisy questions are input into the student model. Meanwhile, the student model is jointly trained by GT data and distilled data, which are derived from the teacher when feeding GT questions.FindingsThe experimental results demonstrate that KDRE can improve the performance of models in the cross-lingual scenario. The performance of each module in KBQA model is improved by KDRE. The knowledge distillation (KD) and noise-generating model in the method can complementarily boost the robustness of models.Originality/valueThe authors first extend KBQA models from monolingual to cross-lingual scenario. Also, the authors first implement KD for KBQA to develop robust cross-lingual models.

Journal

Data Technologies and Applications – Emerald Publishing

Published: Oct 11, 2021

Keywords: Knowledge base question answering; Cross-lingual; Knowledge distillation; Noise-generating model; Robustness; Machine translation

There are no references for this article.