Buhscitu at SEMEVAL-2020 Task 7: Assessing Humour in Edited NewsHeadlines using Hand-Crafted Features and Online Knowledge Bases

Abstract

This paper describes a system that aims at assessing humour intensity in edited news headlinesas part of the 7th task of SemEval2020 on “Humor, Emphasis and Sentiment”. Various factorsneed to be accounted for in order to assess the funniness of an edited headline. We propose anarchitecture that uses hand-crafted features, knowledge bases and a language model to understandhumour, and combines them in a regression model. Our system outperforms two baselines. Ingeneral, automatic humour assessment remains a difficult task.