One-shot Learning for Question-Answering in Gaokao History Challenge

Zhuosheng Zhang, Hai Zhao


Abstract
Answering questions from university admission exams (Gaokao in Chinese) is a challenging AI task since it requires effective representation to capture complicated semantic relations between questions and answers. In this work, we propose a hybrid neural model for deep question-answering task from history examinations. Our model employs a cooperative gated neural network to retrieve answers with the assistance of extra labels given by a neural turing machine labeler. Empirical study shows that the labeler works well with only a small training dataset and the gated mechanism is good at fetching the semantic representation of lengthy answers. Experiments on question answering demonstrate the proposed model obtains substantial performance gains over various neural model baselines in terms of multiple evaluation metrics.
Anthology ID:
C18-1038
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
449–461
Language:
URL:
https://aclanthology.org/C18-1038
DOI:
Bibkey:
Cite (ACL):
Zhuosheng Zhang and Hai Zhao. 2018. One-shot Learning for Question-Answering in Gaokao History Challenge. In Proceedings of the 27th International Conference on Computational Linguistics, pages 449–461, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
One-shot Learning for Question-Answering in Gaokao History Challenge (Zhang & Zhao, COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/C18-1038.pdf
Code
 cooelf/OneshotQA