@inproceedings{pasunuru-etal-2017-towards,
    title = "Towards Improving Abstractive Summarization via Entailment Generation",
    author = "Pasunuru, Ramakanth  and
      Guo, Han  and
      Bansal, Mohit",
    editor = "Wang, Lu  and
      Cheung, Jackie Chi Kit  and
      Carenini, Giuseppe  and
      Liu, Fei",
    booktitle = "Proceedings of the Workshop on New Frontiers in Summarization",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W17-4504/",
    doi = "10.18653/v1/W17-4504",
    pages = "27--32",
    abstract = "Abstractive summarization, the task of rewriting and compressing a document into a short summary, has achieved considerable success with neural sequence-to-sequence models. However, these models can still benefit from stronger natural language inference skills, since a correct summary is logically entailed by the input document, i.e., it should not contain any contradictory or unrelated information. We incorporate such knowledge into an abstractive summarization model via multi-task learning, where we share its decoder parameters with those of an entailment generation model. We achieve promising initial improvements based on multiple metrics and datasets (including a test-only setting). The domain mismatch between the entailment (captions) and summarization (news) datasets suggests that the model is learning some domain-agnostic inference skills."
}