期刊论文

Li, Bo

英文

Information Sciences

0020-0255

2020

527

241-252

10.1016/j.ins.2020.01.035

We thank the anonymous reviewers for their valuable comments. This work was co-supported by Humanity and Social Science Youth Foundation of Ministry of Education of China (no. 19YJC870012), Guangdong Province Key Laboratory of Cyber-Physical System, National Natural Science Foundation of China (no. 61977032 ), Research Planning Project of National Language Committee (no. YB135-40), as well as Fundamental Research Funds for the Central Universities (nos. CCNU19ZN010 , CCNU19TS019 ).

本校为第一且通讯机构

In cross-language question retrieval (CLQR), users employ a new question in one language to search the community question answering (CQA) archives for similar questions in another language. In addition to the ranking problem in monolingual question retrieval, one needs to bridge the language gap in CLQR. The existing adversarial models for cross-language learning normally rely on a single adversarial component. Since natural languages consist of units of different abstract levels, we argue that crossing the language gap adaptatively on different levels with multiple adversarial components shou...