@inproceedings{harbecke-alt-2020-considering,
    title = "Considering Likelihood in {NLP} Classification Explanations with Occlusion and Language Modeling",
    author = "Harbecke, David  and
      Alt, Christoph",
    editor = "Rijhwani, Shruti  and
      Liu, Jiangming  and
      Wang, Yizhong  and
      Dror, Rotem",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.acl-srw.16/",
    doi = "10.18653/v1/2020.acl-srw.16",
    pages = "111--117",
    abstract = "Recently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods are crucial to understand their decisions. Occlusion is a well established method that provides explanations on discrete language data, e.g. by removing a language unit from an input and measuring the impact on a model{'}s decision. We argue that current occlusion-based methods often produce invalid or syntactically incorrect language data, neglecting the improved abilities of recent NLP models. Furthermore, gradient-based explanation methods disregard the discrete distribution of data in NLP. Thus, we propose OLM: a novel explanation method that combines occlusion and language models to sample valid and syntactically correct replacements with high likelihood, given the context of the original input. We lay out a theoretical foundation that alleviates these weaknesses of other explanation methods in NLP and provide results that underline the importance of considering data likelihood in occlusion-based explanation."
}