@inproceedings{helwe-etal-2022-tina,
    title = "{TINA}: Textual Inference with Negation Augmentation",
    author = "Helwe, Chadi  and
      Coumes, Simon  and
      Clavel, Chlo{\'e}  and
      Suchanek, Fabian",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.findings-emnlp.301/",
    doi = "10.18653/v1/2022.findings-emnlp.301",
    pages = "4086--4099",
    abstract = "Transformer-based language models achieve state-of-the-art results on several natural language processing tasks. One of these is textual entailment, i.e., the task of determining whether a premise logically entails a hypothesis. However, the models perform poorly on this task when the examples contain negations. In this paper, we propose a new definition of textual entailment that captures also negation. This allows us to develop TINA (Textual Inference with Negation Augmentation), a principled technique for negated data augmentation that can be combined with the unlikelihood loss function.Our experiments with different transformer-based models show that our method can significantly improve the performance of the models on textual entailment datasets with negation {--} without sacrificing performance on datasets without negation."
}