PunFields at SemEval-2017 Task 7: Employing Roget’s Thesaurus in Automatic Pun Recognition and Interpretation

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 426–431, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics PunFields at SemEval-2017 Task 7: Employing Roget’s Thesaurus in Automatic Pun Recognition and Interpretation Elena Mikhalkova Institute of Philology and Journalism Tyumen State University Tyumen, Russia, 625003 e.v.mikhalkova@utmn.ru Yuri Karyakin Institute of Mathematics and Computer Science Tyumen State University Tyumen, Russia, 625003 y.e.karyakin@utmn.ru Abstract The article describes a model of automatic interpretation of English puns, based on Roget’s Thesaurus, and its implementa- tion, PunFields. In a pun, the algorithm discovers two groups of words that belong to two main semantic fields. The fields be- come a semantic vector based on which an SVM classifier learns to recognize puns. A rule-based model is then applied for recog- nition of intentionally ambiguous (target) words and their definitions. In SemEval Task 7 PunFields shows a considerably good result in pun classification, but re- quires improvement in searching for the target word and its definition. 1 Introduction The following terminology is basic in our research of puns. A pun is a) a short humorous genre where a word or phrase is intentionally used in two meanings, b) a means of expression the essence of which is to use a word or phrase so that in the given context the word or phrase can be un- derstood in two meanings simultaneously. A tar- get word is a word that appears in two meanings. A homographic pun is a pun that “exploits dis- tinct meanings of the same written word” (Miller and Gurevych, 2015) (these can be meanings of a polysemantic word or homonyms, including homonymic word forms). A heterographic pun is a pun in which the target word resembles an- other word or phrase in spelling; we will call the latter the second target word. Consider the fol- lowing example (the Banker joke): “I used to be a banker, but I lost inter- est.” The Banker joke is a homographic pun; interest is the target word. Unlike it, the Church joke be- low is a heterographic pun; propane is the target word, profane is the second target word: “When the church bought gas for their annual barbecue, proceeds went from the sacred to the propane.” Our model of automatic pun analysis is based on the following premise: in a pun, there are two groups of words and their meanings that indicate the two meanings of the target word. These groups can overlap, i.e. contain the same polysemantic words used in different meanings. In the Banker joke, words and collocations banker, lost interest point at the professional sta- tus of the narrator and his/her career failure. At the same time, used to, lost interest tell a story of losing emotional attachment to the profession: the narrator became disinterested. The algorithm of pun recognition that we suggest discovers these two groups of words based on common semes1 (Subtask 1), finds the words that belong to the both groups, and chooses the target word …

Content truncated to 500 words