Buhscitu at SemEvaL-2020 Task 7: Assessing Humour in Edited News Headlines using Hand-Crafted Features and Online Knowledge Bases

Kristian Nørgaard Jensen; Nicolaj Filrup Rasmussen; Thai Wang; Marco Placenti; Barbara Plank

Buhscitu at SemEvaL-2020 Task 7: Assessing Humour in Edited News Headlines using Hand-Crafted Features and Online Knowledge Bases

Kristian Nørgaard Jensen
, Nicolaj Filrup Rasmussen
, Thai Wang
, Marco Placenti
, Barbara Plank

NLPnorth

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

Abstract

This paper describes our system to assess humour intensity in edited news headlines as part of a participation in the 7th task of SemEval-2020 on “Humor, Emphasis and Sentiment”. Various factors need to be accounted for in order to assess the funniness of an edited headline. We propose an architecture that uses hand-crafted features, knowledge bases and a language model to understand humour, and combines them in a regression model. Our system outperforms two baselines. In general, automatic humour assessment remains a difficult task.

Originalsprog	Engelsk
Titel	SemEval
Forlag	Association for Computational Linguistics
Publikationsdato	2020
Status	Udgivet - 2020
Begivenhed	Natural language processing - Barcelona, Spanien Varighed: 12 dec. 2020 → 13 dec. 2020 Konferencens nummer: 28th

Workshop

Workshop	Natural language processing
Nummer	28th
Land/Område	Spanien
By	Barcelona
Periode	12/12/2020 → 13/12/2020

Emneord

humour intensity assessment
edited news headlines
SemEval-2020
regression model
automatic humour detection

Adgang til dokumentet

Final-SemEval2020-Task7Accepteret manuskript, 257 KBLicens: CC BY

Citationsformater

@inproceedings{4cecc8aeb3db4a37b01edbb700caec50,

title = "Buhscitu at SemEvaL-2020 Task 7: Assessing Humour in Edited News Headlines using Hand-Crafted Features and Online Knowledge Bases",

abstract = "This paper describes our system to assess humour intensity in edited news headlines as part of a participation in the 7th task of SemEval-2020 on “Humor, Emphasis and Sentiment”. Various factors need to be accounted for in order to assess the funniness of an edited headline. We propose an architecture that uses hand-crafted features, knowledge bases and a language model to understand humour, and combines them in a regression model. Our system outperforms two baselines. In general, automatic humour assessment remains a difficult task. ",

keywords = "humour intensity assessment, edited news headlines, SemEval-2020, regression model, automatic humour detection, humour intensity assessment, edited news headlines, SemEval-2020, regression model, automatic humour detection",

author = "Jensen, \{Kristian N{\o}rgaard\} and \{Filrup Rasmussen\}, Nicolaj and Thai Wang and Marco Placenti and Barbara Plank",

year = "2020",

language = "English",

booktitle = "SemEval",

publisher = "Association for Computational Linguistics",

address = "United States",

note = "Natural language processing ; Conference date: 12-12-2020 Through 13-12-2020",

}

Buhscitu at SemEvaL-2020 Task 7: Assessing Humour in Edited News Headlines using Hand-Crafted Features and Online Knowledge Bases. / Jensen, Kristian Nørgaard; Filrup Rasmussen, Nicolaj; Wang, Thai et al.
SemEval. Association for Computational Linguistics, 2020.

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Buhscitu at SemEvaL-2020 Task 7: Assessing Humour in Edited News Headlines using Hand-Crafted Features and Online Knowledge Bases

AU - Jensen, Kristian Nørgaard

AU - Filrup Rasmussen, Nicolaj

AU - Wang, Thai

AU - Placenti, Marco

AU - Plank, Barbara

N1 - Conference code: 28th

PY - 2020

Y1 - 2020

N2 - This paper describes our system to assess humour intensity in edited news headlines as part of a participation in the 7th task of SemEval-2020 on “Humor, Emphasis and Sentiment”. Various factors need to be accounted for in order to assess the funniness of an edited headline. We propose an architecture that uses hand-crafted features, knowledge bases and a language model to understand humour, and combines them in a regression model. Our system outperforms two baselines. In general, automatic humour assessment remains a difficult task.

AB - This paper describes our system to assess humour intensity in edited news headlines as part of a participation in the 7th task of SemEval-2020 on “Humor, Emphasis and Sentiment”. Various factors need to be accounted for in order to assess the funniness of an edited headline. We propose an architecture that uses hand-crafted features, knowledge bases and a language model to understand humour, and combines them in a regression model. Our system outperforms two baselines. In general, automatic humour assessment remains a difficult task.

KW - humour intensity assessment

KW - edited news headlines

KW - SemEval-2020

KW - regression model

KW - automatic humour detection

KW - humour intensity assessment

KW - edited news headlines

KW - SemEval-2020

KW - regression model

KW - automatic humour detection

M3 - Article in proceedings

BT - SemEval

PB - Association for Computational Linguistics

T2 - Natural language processing

Y2 - 12 December 2020 through 13 December 2020

ER -

Buhscitu at SemEvaL-2020 Task 7: Assessing Humour in Edited News Headlines using Hand-Crafted Features and Online Knowledge Bases

Abstract

Workshop

Emneord

Adgang til dokumentet

Fingeraftryk

Citationsformater