@inproceedings{weir-etal-2020-cod3s,
    title = "{COD3S}: Diverse Generation with Discrete Semantic Signatures",
    author = "Weir, Nathaniel  and
      Sedoc, Jo{\~a}o  and
      Van Durme, Benjamin",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.emnlp-main.421/",
    doi = "10.18653/v1/2020.emnlp-main.421",
    pages = "5199--5211",
    abstract = "We present COD3S, a novel method for generating semantically diverse sentences using neural sequence-to-sequence (seq2seq) models. Conditioned on an input, seq2seqs typically produce semantically and syntactically homogeneous sets of sentences and thus perform poorly on one-to-many sequence generation tasks. Our two-stage approach improves output diversity by conditioning generation on locality-sensitive hash (LSH)-based semantic sentence codes whose Hamming distances highly correlate with human judgments of semantic textual similarity. Though it is generally applicable, we apply to causal generation, the task of predicting a proposition{'}s plausible causes or effects. We demonstrate through automatic and human evaluation that responses produced using our method exhibit improved diversity without degrading task performance."
}