It takes nine to smell a rat: Neural multi-task learning for check-worthiness prediction

Slavena Vasileva, Pepa Atanasova, Lluís Màrquez, Alberto Barrón-Cedeño, Preslav Nakov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a multi-task deep-learning approach for estimating the check-worthiness of claims in political debates. Given a political debate, such as the 2016 US Presidential and Vice-Presidential ones, the task is to predict which statements in the debate should be prioritized for fact-checking. While different fact-checking organizations would naturally make different choices when analyzing the same debate, we show that it pays to learn from multiple sources simultaneously (PolitiFact, FactCheck, ABC, CNN, NPR, NYT, Chicago Tribune, The Guardian, and Washington Post) in a multi-task learning setup, even when a particular source is chosen as a target to imitate. Our evaluation shows state-of-the-art results on a standard dataset for the task of check-worthiness prediction.

Original languageEnglish
Title of host publicationInternational Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings
EditorsGalia Angelova, Ruslan Mitkov, Ivelina Nikolova, Irina Temnikova, Irina Temnikova
PublisherIncoma Ltd
Pages1229-1239
Number of pages11
ISBN (Electronic)9789544520557
DOIs
Publication statusPublished - 1 Jan 2019
Event12th International Conference on Recent Advances in Natural Language Processing, RANLP 2019 - Varna, Bulgaria
Duration: 2 Sep 20194 Sep 2019

Publication series

NameInternational Conference Recent Advances in Natural Language Processing, RANLP
Volume2019-September
ISSN (Print)1313-8502

Conference

Conference12th International Conference on Recent Advances in Natural Language Processing, RANLP 2019
CountryBulgaria
CityVarna
Period2/9/194/9/19

Fingerprint

Deep learning

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Vasileva, S., Atanasova, P., Màrquez, L., Barrón-Cedeño, A., & Nakov, P. (2019). It takes nine to smell a rat: Neural multi-task learning for check-worthiness prediction. In G. Angelova, R. Mitkov, I. Nikolova, I. Temnikova, & I. Temnikova (Eds.), International Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings (pp. 1229-1239). (International Conference Recent Advances in Natural Language Processing, RANLP; Vol. 2019-September). Incoma Ltd. https://doi.org/10.26615/978-954-452-056-4_141

It takes nine to smell a rat : Neural multi-task learning for check-worthiness prediction. / Vasileva, Slavena; Atanasova, Pepa; Màrquez, Lluís; Barrón-Cedeño, Alberto; Nakov, Preslav.

International Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings. ed. / Galia Angelova; Ruslan Mitkov; Ivelina Nikolova; Irina Temnikova; Irina Temnikova. Incoma Ltd, 2019. p. 1229-1239 (International Conference Recent Advances in Natural Language Processing, RANLP; Vol. 2019-September).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vasileva, S, Atanasova, P, Màrquez, L, Barrón-Cedeño, A & Nakov, P 2019, It takes nine to smell a rat: Neural multi-task learning for check-worthiness prediction. in G Angelova, R Mitkov, I Nikolova, I Temnikova & I Temnikova (eds), International Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings. International Conference Recent Advances in Natural Language Processing, RANLP, vol. 2019-September, Incoma Ltd, pp. 1229-1239, 12th International Conference on Recent Advances in Natural Language Processing, RANLP 2019, Varna, Bulgaria, 2/9/19. https://doi.org/10.26615/978-954-452-056-4_141
Vasileva S, Atanasova P, Màrquez L, Barrón-Cedeño A, Nakov P. It takes nine to smell a rat: Neural multi-task learning for check-worthiness prediction. In Angelova G, Mitkov R, Nikolova I, Temnikova I, Temnikova I, editors, International Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings. Incoma Ltd. 2019. p. 1229-1239. (International Conference Recent Advances in Natural Language Processing, RANLP). https://doi.org/10.26615/978-954-452-056-4_141
Vasileva, Slavena ; Atanasova, Pepa ; Màrquez, Lluís ; Barrón-Cedeño, Alberto ; Nakov, Preslav. / It takes nine to smell a rat : Neural multi-task learning for check-worthiness prediction. International Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings. editor / Galia Angelova ; Ruslan Mitkov ; Ivelina Nikolova ; Irina Temnikova ; Irina Temnikova. Incoma Ltd, 2019. pp. 1229-1239 (International Conference Recent Advances in Natural Language Processing, RANLP).
@inproceedings{3b6bfd669e0f4c6e8bf306f29f7fe9d7,
title = "It takes nine to smell a rat: Neural multi-task learning for check-worthiness prediction",
abstract = "We propose a multi-task deep-learning approach for estimating the check-worthiness of claims in political debates. Given a political debate, such as the 2016 US Presidential and Vice-Presidential ones, the task is to predict which statements in the debate should be prioritized for fact-checking. While different fact-checking organizations would naturally make different choices when analyzing the same debate, we show that it pays to learn from multiple sources simultaneously (PolitiFact, FactCheck, ABC, CNN, NPR, NYT, Chicago Tribune, The Guardian, and Washington Post) in a multi-task learning setup, even when a particular source is chosen as a target to imitate. Our evaluation shows state-of-the-art results on a standard dataset for the task of check-worthiness prediction.",
author = "Slavena Vasileva and Pepa Atanasova and Llu{\'i}s M{\`a}rquez and Alberto Barr{\'o}n-Cede{\~n}o and Preslav Nakov",
year = "2019",
month = "1",
day = "1",
doi = "10.26615/978-954-452-056-4_141",
language = "English",
series = "International Conference Recent Advances in Natural Language Processing, RANLP",
publisher = "Incoma Ltd",
pages = "1229--1239",
editor = "Galia Angelova and Ruslan Mitkov and Ivelina Nikolova and Irina Temnikova and Irina Temnikova",
booktitle = "International Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings",

}

TY - GEN

T1 - It takes nine to smell a rat

T2 - Neural multi-task learning for check-worthiness prediction

AU - Vasileva, Slavena

AU - Atanasova, Pepa

AU - Màrquez, Lluís

AU - Barrón-Cedeño, Alberto

AU - Nakov, Preslav

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We propose a multi-task deep-learning approach for estimating the check-worthiness of claims in political debates. Given a political debate, such as the 2016 US Presidential and Vice-Presidential ones, the task is to predict which statements in the debate should be prioritized for fact-checking. While different fact-checking organizations would naturally make different choices when analyzing the same debate, we show that it pays to learn from multiple sources simultaneously (PolitiFact, FactCheck, ABC, CNN, NPR, NYT, Chicago Tribune, The Guardian, and Washington Post) in a multi-task learning setup, even when a particular source is chosen as a target to imitate. Our evaluation shows state-of-the-art results on a standard dataset for the task of check-worthiness prediction.

AB - We propose a multi-task deep-learning approach for estimating the check-worthiness of claims in political debates. Given a political debate, such as the 2016 US Presidential and Vice-Presidential ones, the task is to predict which statements in the debate should be prioritized for fact-checking. While different fact-checking organizations would naturally make different choices when analyzing the same debate, we show that it pays to learn from multiple sources simultaneously (PolitiFact, FactCheck, ABC, CNN, NPR, NYT, Chicago Tribune, The Guardian, and Washington Post) in a multi-task learning setup, even when a particular source is chosen as a target to imitate. Our evaluation shows state-of-the-art results on a standard dataset for the task of check-worthiness prediction.

UR - http://www.scopus.com/inward/record.url?scp=85070498498&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070498498&partnerID=8YFLogxK

U2 - 10.26615/978-954-452-056-4_141

DO - 10.26615/978-954-452-056-4_141

M3 - Conference contribution

AN - SCOPUS:85070498498

T3 - International Conference Recent Advances in Natural Language Processing, RANLP

SP - 1229

EP - 1239

BT - International Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings

A2 - Angelova, Galia

A2 - Mitkov, Ruslan

A2 - Nikolova, Ivelina

A2 - Temnikova, Irina

A2 - Temnikova, Irina

PB - Incoma Ltd

ER -