Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template

Yunfan Gu, Yang Yuqiao, Zhongyu Wei


Abstract
Question paraphrasing aims to restate a given question with different expressions but keep the original meaning. Recent approaches are mostly based on neural networks following a sequence-to-sequence fashion, however, these models tend to generate unpredictable results. To overcome this drawback, we propose a pipeline model based on templates. It follows three steps, a) identifies template from the input question, b) retrieves candidate templates, c) fills candidate templates with original topic words. Experiment results on two self-constructed datasets show that our model outperforms the sequence-to-sequence model in a large margin and the advantage is more promising when the size of training sample is small.
Anthology ID:
D19-5514
Volume:
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | WNUT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
109–114
Language:
URL:
https://www.aclweb.org/anthology/D19-5514
DOI:
10.18653/v1/D19-5514
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-5514.pdf