@inproceedings{he-etal-2019-pun,
    title = "Pun Generation with Surprise",
    author = "He, He  and
      Peng, Nanyun  and
      Liang, Percy",
    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/add-emnlp-2024-awards/N19-1172/",
    doi = "10.18653/v1/N19-1172",
    pages = "1734--1744",
    abstract = "We tackle the problem of generating a pun sentence given a pair of homophones (e.g., {\textquotedblleft}died{\textquotedblright} and {\textquotedblleft}dyed{\textquotedblright}). Puns are by their very nature statistically anomalous and not amenable to most text generation methods that are supervised by a large corpus. In this paper, we propose an unsupervised approach to pun generation based on lots of raw (unhumorous) text and a surprisal principle. Specifically, we posit that in a pun sentence, there is a strong association between the pun word (e.g., {\textquotedblleft}dyed{\textquotedblright}) and the distant context, but a strong association between the alternative word (e.g., {\textquotedblleft}died{\textquotedblright}) and the immediate context. We instantiate the surprisal principle in two ways: (i) as a measure based on the ratio of probabilities given by a language model, and (ii) a retrieve-and-edit approach based on words suggested by a skip-gram model. Based on human evaluation, our retrieve-and-edit approach generates puns successfully 30{\%} of the time, doubling the success rate of a neural generation baseline."
}