@inproceedings{briakou-etal-2023-explaining,
    title = "Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences",
    author = "Briakou, Eleftheria  and
      Goyal, Navita  and
      Carpuat, Marine",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.emnlp-main.690/",
    doi = "10.18653/v1/2023.emnlp-main.690",
    pages = "11220--11237",
    abstract = "Explainable NLP techniques primarily explain by answering {\textquotedblleft}Which tokens in the input are responsible for this prediction?{\textquotedblright}. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by answering {\textquotedblleft}What differences between the two inputs explain this prediction?{\textquotedblright}. We introduce a technique to generate contrastive phrasal highlights that explain the predictions of a semantic divergence model via phrase alignment guided erasure. We show that the resulting highlights match human rationales of cross-lingual semantic differences better than popular post-hoc saliency techniques and that they successfully help people detect fine-grained meaning differences in human translations and critical machine translation errors."
}