@inproceedings{kang-etal-2018-adventure,
    title = "{A}dv{E}ntu{R}e: Adversarial Training for Textual Entailment with Knowledge-Guided Examples",
    author = "Kang, Dongyeop  and
      Khot, Tushar  and
      Sabharwal, Ashish  and
      Hovy, Eduard",
    editor = "Gurevych, Iryna  and
      Miyao, Yusuke",
    booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/P18-1225/",
    doi = "10.18653/v1/P18-1225",
    pages = "2418--2428",
    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 to the discriminator`s weaknesses. 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{\%} sub-sample of SNLI. Notably, even a single hand-written rule, negate, improves the accuracy of negation examples in SNLI by 6.1{\%}."
}