English

AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples

Computation and Language 2018-05-15 v1 Artificial Intelligence Machine Learning

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%.

Keywords

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

R2 v1 2026-06-23T01:52:46.577Z