Adaptive Cross-Lingual Question Generation with Minimal Resources. (19th July 2021)

• Record Type: Journal Article
• Authors: Yu, Jianxing; Wang, Shiqi; Yin, Jian
• Is Part Of: Computer journal. Volume 64:Number 7(2021)
• Page Start: 1056
• Page End: 1068
• Publication Date: 2021-07-19
• Subjects: multimedia knowledge discovery -- cross-lingual question generation -- adaptive QG model -- task-specific meta-learning -- structured similarity; Computers -- Periodicals; 005.1
• DOI: 10.1093/comjnl/bxab106
• Languages: English
• ISSNs: 0010-4620

Abstract

Abstract: The task of question generation (QG) aims to create valid questions and correlated answers from the given text. Despite the neural QG approaches have achieved promising results, they are typically developed for languages with rich annotated training data. Because of the high annotation cost, it is difficult to deploy to other low-resource languages. Besides, different samples have their own characteristics on the aspects of text contextual structure, question type and correlations. Without capturing these diversified characteristics, the traditional one-size-fits-all model is hard to generate the best results. To address this problem, we study the task of cross-lingual QG from an adaptive learning perspective. Concretely, we first build a basic QG model on a multilingual space using the labelled data. In this way, we can transfer the supervision from the high-resource language to the language lacking labelled data. We then design a task-specific meta-learner to optimize the basic QG model. Each sample and its similar instances are viewed as a pseudo-QG task. The asking patterns and logical forms contained in the similar samples can be used as a guide to fine-tune the model fitly and produce the optimal results accordingly. Considering that each sample contains the text, question and answer, with unknown semantic correlations among them, we propose a context-dependent retriever to measure the similarity of such structured inputs. Experimental results on three languages of three typical data sets show the effectiveness of our approach.