SRHR at SemEval-2017 Task 6: Word Associations for Humour Recognition

Abstract

This paper explores the role of semantic relatedness features, such as word associations, in humour recognition. Specifically, we examine the task of inferring pairwise humour judgments in Twitter hashtag wars. We examine a variety of word association features derived from the University of Southern Florida Free Association Norms (USF) (Nelson et al., 2004) and the Edinburgh Associative Thesaurus (EAT) (Kiss et al., 1973) and find that word associationbased features outperform Word2Vec similarity, a popular semantic relatedness measure. Our system achieves an accuracy of 56.42% using a combination of unigram perplexity, bigram perplexity, EAT

SemEval-2017 Task 6: #HashtagWars: Learning a Sense of Humor

“…As for the feature-based systems, one trend we observed is that many teams tried to capture the incongruity aspect of humor (Cattle and Ma, 2017) , often present in the dataset. The approaches used by teams varied from n-gram language models, word association, to semantic relatedness features.…”

Mining Effective Features Using Quantum Entropy for Humor Recognition

“…Features based on semantic similarity (Mihalcea et al, 2010;Yang et al, 2015) and word association (Liu et al, 2018;Cattle and Ma, 2018) have achieved certain results, but they lack consideration of humorous mechanisms. Xie et al ( 2021) calculated the uncertainty and the surprisal values of the joke with the help of the GPT-2.…”