@inproceedings{2133031573ee40ffbbf81a3e27bf1534,
title = "CATs are Fuzzy PETs: A Corpus and Analysis of Potentially Euphemistic Terms",
abstract = "Euphemisms have not received much attention in natural language processing, despite being an important element of polite and figurative language. Euphemisms prove to be a difficult topic, not only because they are subject to language change, but also because humans may not agree on what is a euphemism and what is not. Nonetheless, the first step to tackling the issue is to collect and analyze examples of euphemisms. We present a corpus of potentially euphemistic terms (PETs) along with example texts from the GloWbE corpus. Additionally, we present a subcorpus of texts where these PETs are not being used euphemistically, which may be useful for future applications. We also discuss the results of multiple analyses run on the corpus. Firstly, we find that sentiment analysis on the euphemistic texts supports that PETs generally decrease negative and offensive sentiment. Secondly, we observe cases of disagreement in an annotation task, where humans are asked to label PETs as euphemistic or not in a subset of our corpus text examples. We attribute the disagreement to a variety of potential reasons, including if the PET was a commonly accepted term (CAT).",
keywords = "euphemisms, NLP, politeness",
author = "Martha Gavidia and Patrick Lee and Anna Feldman and Jing Peng",
note = "Funding Information: We thank our annotators Raz Besaleli, Kira Horiuchi, Kelly Ortega, and Kenna Reagan for their time and attention to our corpus annotation task as well as Brad McNamee and Avery Field for their contributions to our PETs dataset. This material is based upon work supported by the National Science Foundation under Grant No. 1704113. Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.; null ; Conference date: 20-06-2022 Through 25-06-2022",
year = "2022",
language = "English",
series = "2022 Language Resources and Evaluation Conference, LREC 2022",
publisher = "European Language Resources Association (ELRA)",
pages = "2658--2671",
editor = "Nicoletta Calzolari and Frederic Bechet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Jan Odijk and Stelios Piperidis",
booktitle = "2022 Language Resources and Evaluation Conference, LREC 2022",
}