AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples
Abstract
We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for incorporating large lexical resources in entailment models via only a handful of rule templates. Second, to make the entailment model - a discriminator - more robust, we propose the first GAN-style approach for training it using a natural language example generator that iteratively adjusts based on the discriminator's performance. We demonstrate effectiveness using two entailment datasets, where the proposed methods increase accuracy by 4.7% on SciTail and by 2.8% on a 1% training sub-sample of SNLI. Notably, even a single hand-written rule, negate, improves the accuracy on the negation examples in SNLI by 6.1%.
Cite
@article{arxiv.1805.04680,
title = {AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples},
author = {Dongyeop Kang and Tushar Khot and Ashish Sabharwal and Eduard Hovy},
journal= {arXiv preprint arXiv:1805.04680},
year = {2018}
}
Comments
ACL 2018