@InProceedings{chandrasekaran-parikh-bansal:2018:N18-2,
  author    = {Chandrasekaran, Arjun  and  Parikh, Devi  and  Bansal, Mohit},
  title     = {Punny Captions: Witty Wordplay in Image Descriptions},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {770--775},
  abstract  = {Wit is a form of rich interaction that is often grounded in a specific situation (e.g., a comment in response to an event). In this work, we attempt to build computational models that can produce witty descriptions for a given image. Inspired by a cognitive account of humor appreciation, we employ linguistic wordplay, specifically puns, in image descriptions. We develop two approaches which involve retrieving witty descriptions for a given image from a large corpus of sentences, or generating them via an encoder-decoder neural network architecture. We compare our approach against meaningful baseline approaches via human studies and show substantial improvements. Moreover, in a Turing test style evaluation, people find the image descriptions generated by our model to be slightly wittier than human-written witty descriptions when the human is subject to similar constraints as the model regarding word usage and style.},
  url       = {http://www.aclweb.org/anthology/N18-2121}
}