pith. sign in

arxiv: 1805.04680 · v1 · pith:3U6YDFCAnew · submitted 2018-05-12 · 💻 cs.CL · cs.AI· cs.LG

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

classification 💻 cs.CL cs.AIcs.LG
keywords entailmenttrainingexamplesaccuracyadversarialdiscriminatorexamplefirst
0
0 comments X
read the original 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%.

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.