@inproceedings{chandrasekaran-etal-2018-punny,
title = "Punny Captions: Witty Wordplay in Image Descriptions",
author = "Chandrasekaran, Arjun and
Parikh, Devi and
Bansal, Mohit",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-2121",
doi = "10.18653/v1/N18-2121",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chandrasekaran-etal-2018-punny">
<titleInfo>
<title>Punny Captions: Witty Wordplay in Image Descriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Chandrasekaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Devi</namePart>
<namePart type="family">Parikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">chandrasekaran-etal-2018-punny</identifier>
<identifier type="doi">10.18653/v1/N18-2121</identifier>
<location>
<url>https://aclanthology.org/N18-2121</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>770</start>
<end>775</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Punny Captions: Witty Wordplay in Image Descriptions
%A Chandrasekaran, Arjun
%A Parikh, Devi
%A Bansal, Mohit
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F chandrasekaran-etal-2018-punny
%X 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.
%R 10.18653/v1/N18-2121
%U https://aclanthology.org/N18-2121
%U https://doi.org/10.18653/v1/N18-2121
%P 770-775
Markdown (Informal)
[Punny Captions: Witty Wordplay in Image Descriptions](https://aclanthology.org/N18-2121) (Chandrasekaran et al., NAACL 2018)
ACL
- Arjun Chandrasekaran, Devi Parikh, and Mohit Bansal. 2018. Punny Captions: Witty Wordplay in Image Descriptions. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 770–775, New Orleans, Louisiana. Association for Computational Linguistics.