@inproceedings{raghu-etal-2019-disentangling,
    title = "{D}isentangling {L}anguage and {K}nowledge in {T}ask-{O}riented {D}ialogs",
    author = "Raghu, Dinesh  and
      Gupta, Nikhil  and
      Mausam",
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/N19-1126/",
    doi = "10.18653/v1/N19-1126",
    pages = "1239--1255",
    abstract = "The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such changes. We propose an encoder-decoder architecture (BoSsNet) with a novel Bag-of-Sequences (BoSs) memory, which facilitates the disentangled learning of the response`s language model and its knowledge incorporation. Consequently, the KB can be modified with new knowledge without a drop in interpretability. We find that BoSsNeT outperforms state-of-the-art models, with considerable improvements ({\ensuremath{>}}10{\%}) on bAbI OOV test sets and other human-human datasets. We also systematically modify existing datasets to measure disentanglement and show BoSsNeT to be robust to KB modifications."
}