pith. sign in

arxiv: 1910.13108 · v1 · pith:OFZVB4QKnew · submitted 2019-10-29 · 💻 cs.CL · cs.AI

Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss

classification 💻 cs.CL cs.AI
keywords answerdefinitivegeneratedlossquestionquestionsanswer-awarebases
0
0 comments X
read the original abstract

We tackle the task of question generation over knowledge bases. Conventional methods for this task neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to be definitive. In this paper, we strive toward the above two issues via incorporating diversified contexts and answer-aware loss. Specifically, we propose a neural encoder-decoder model with multi-level copy mechanisms to generate such questions. Furthermore, the answer aware loss is introduced to make generated questions corresponding to more definitive answers. Experiments demonstrate that our model achieves state-of-the-art performance. Meanwhile, such generated question can express the given predicate and correspond to a definitive answer.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.