TU Darmstadt / ULB / TUbiblio

A Bayesian Approach for Predicting the Humorousness of One-liners

Simpson, Edwin and Do Dinh, Erik-Lân and Miller, Tristan and Gurevych, Iryna (2019):
A Bayesian Approach for Predicting the Humorousness of One-liners.
In: 2019 Conference of the International Society for Humor Studies, Austin, TX, USA, 2019-06-24 to 2019-06-28, [Conference or Workshop Item]

Abstract

Humour is an essential aspect of human communication that computational methods have yet to master. Most natural language processing systems to date make at best discrete, coarse-grained distinctions between the comical and the conventional, yet such notions are better conceptualized as a broad spectrum. We therefore introduce the novel task of automatically quantifying and ranking short texts by humorousness, and present a probabilistic approach that learns to do this by examining human preference judgments. We evaluate our system on a crowdsourced data set of nearly 30,000 pairwise comparisons of over 4000 one-liners. We find that it correlates well with best–worst scaling (BWS) when pairwise labels are abundant, and outperforms BWS when they are sparse. And unlike BWS, because our method exploits word embeddings and shallow text features, it can make accurate predictions even for previously unseen texts.

Item Type: Conference or Workshop Item
Erschienen: 2019
Creators: Simpson, Edwin and Do Dinh, Erik-Lân and Miller, Tristan and Gurevych, Iryna
Title: A Bayesian Approach for Predicting the Humorousness of One-liners
Language: English
Abstract:

Humour is an essential aspect of human communication that computational methods have yet to master. Most natural language processing systems to date make at best discrete, coarse-grained distinctions between the comical and the conventional, yet such notions are better conceptualized as a broad spectrum. We therefore introduce the novel task of automatically quantifying and ranking short texts by humorousness, and present a probabilistic approach that learns to do this by examining human preference judgments. We evaluate our system on a crowdsourced data set of nearly 30,000 pairwise comparisons of over 4000 one-liners. We find that it correlates well with best–worst scaling (BWS) when pairwise labels are abundant, and outperforms BWS when they are sparse. And unlike BWS, because our method exploits word embeddings and shallow text features, it can make accurate predictions even for previously unseen texts.

Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Title: 2019 Conference of the International Society for Humor Studies
Event Location: Austin, TX, USA
Event Dates: 2019-06-24 to 2019-06-28
Date Deposited: 23 May 2019 13:44
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item