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

摘要

The article describes a model of automatic interpretation of English puns,based on Roget's Thesaurus, and its implementation, PunFields. In a pun, thealgorithm discovers two groups of words that belong to two main semanticfields. The fields become a semantic vector based on which an SVM classifierlearns to recognize puns. A rule-based model is then applied for recognition ofintentionally ambiguous (target) words and their definitions. In SemEval Task 7PunFields shows a considerably good result in pun classification, but requiresimprovement in searching for the target word and its definition.