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

@inproceedings{Kang2018AdvEntuReAT,
  title={AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples},
  author={Dongyeop Kang and Tushar Khot and Ashish Sabharwal and Eduard H. Hovy},
  booktitle={ACL},
  year={2018}
}
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… CONTINUE READING
6
Twitter Mentions

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • 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.

Citations

Publications citing this paper.
SHOWING 1-10 OF 11 CITATIONS

Dialog State Tracking with Reinforced Data Augmentation

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Deep Adversarial Learning for NLP

VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES