Humour Agent Detection in Puns

摘要

Humour is an integral part of all varieties of linguistic expression. A very popular type of humour is pun. Pun uses word-play and ambiguity to create a humorous effect. Due to the extensive usage that puns find in texts, it becomes imperative that computers understand and learn to process them. While some work has been done to detect the presence of puns in a text, finding the ambiguous word which caused the humour remains a new task. It is important to understand the cause of humour before we can proceed to the next steps, such as humour generation. This paper aims to propose a method to identify the humour agent in pun-based sentences. The method utilizes the structural information of the sentence and then uses a semantic similarity measure to find a relationship between the words. This relationship is used to find the humour agent in the sentence.