Fully automated fact checking using external sources

Georgi Karadzhov, Preslav Nakov, Lluis Marques, Alberto Barron, Ivan Koychev

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

16 Citations (Scopus)

Abstract

Given the constantly growing proliferation of false claims online in recent years, there has been also a growing research interest in automatically distinguishing false rumors from factually true claims. Here, we propose a general-purpose framework for fully-automatic fact checking using external sources, tapping the potential of the entire Web as a knowledge source to confirm or reject a claim. Our framework uses a deep neural network with LSTM text encoding to combine semantic kernels with task-specific embeddings that encode a claim together with pieces of potentially-relevant text fragments from the Web, taking the source reliability into account. The evaluation results show good performance on two different tasks and datasets: (i) rumor detection and (if) fact checking of the answers to a question in community question answering forums.

Original languageEnglish
Title of host publicationInternational Conference on Recent Advances in Natural Language Processing
Subtitle of host publicationMeet Deep Learning, RANLP 2017 - Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages344-353
Number of pages10
Volume2017-September
ISBN (Electronic)9789544520489
DOIs
Publication statusPublished - 1 Jan 2017
Event11th International Conference on Recent Advances in Natural Language Processing, RANLP 2017 - Varna, Bulgaria
Duration: 2 Sep 20178 Sep 2017

Other

Other11th International Conference on Recent Advances in Natural Language Processing, RANLP 2017
CountryBulgaria
CityVarna
Period2/9/178/9/17

Fingerprint

Semantics
Deep neural networks

ASJC Scopus subject areas

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

Cite this

Karadzhov, G., Nakov, P., Marques, L., Barron, A., & Koychev, I. (2017). Fully automated fact checking using external sources. In International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings (Vol. 2017-September, pp. 344-353). Association for Computational Linguistics (ACL). https://doi.org/10.26615/978-954-452-049-6-046

Fully automated fact checking using external sources. / Karadzhov, Georgi; Nakov, Preslav; Marques, Lluis; Barron, Alberto; Koychev, Ivan.

International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings. Vol. 2017-September Association for Computational Linguistics (ACL), 2017. p. 344-353.

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

Karadzhov, G, Nakov, P, Marques, L, Barron, A & Koychev, I 2017, Fully automated fact checking using external sources. in International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings. vol. 2017-September, Association for Computational Linguistics (ACL), pp. 344-353, 11th International Conference on Recent Advances in Natural Language Processing, RANLP 2017, Varna, Bulgaria, 2/9/17. https://doi.org/10.26615/978-954-452-049-6-046
Karadzhov G, Nakov P, Marques L, Barron A, Koychev I. Fully automated fact checking using external sources. In International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings. Vol. 2017-September. Association for Computational Linguistics (ACL). 2017. p. 344-353 https://doi.org/10.26615/978-954-452-049-6-046
Karadzhov, Georgi ; Nakov, Preslav ; Marques, Lluis ; Barron, Alberto ; Koychev, Ivan. / Fully automated fact checking using external sources. International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings. Vol. 2017-September Association for Computational Linguistics (ACL), 2017. pp. 344-353
@inproceedings{b59638abc73b496c82a17e665ee950de,
title = "Fully automated fact checking using external sources",
abstract = "Given the constantly growing proliferation of false claims online in recent years, there has been also a growing research interest in automatically distinguishing false rumors from factually true claims. Here, we propose a general-purpose framework for fully-automatic fact checking using external sources, tapping the potential of the entire Web as a knowledge source to confirm or reject a claim. Our framework uses a deep neural network with LSTM text encoding to combine semantic kernels with task-specific embeddings that encode a claim together with pieces of potentially-relevant text fragments from the Web, taking the source reliability into account. The evaluation results show good performance on two different tasks and datasets: (i) rumor detection and (if) fact checking of the answers to a question in community question answering forums.",
author = "Georgi Karadzhov and Preslav Nakov and Lluis Marques and Alberto Barron and Ivan Koychev",
year = "2017",
month = "1",
day = "1",
doi = "10.26615/978-954-452-049-6-046",
language = "English",
volume = "2017-September",
pages = "344--353",
booktitle = "International Conference on Recent Advances in Natural Language Processing",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Fully automated fact checking using external sources

AU - Karadzhov, Georgi

AU - Nakov, Preslav

AU - Marques, Lluis

AU - Barron, Alberto

AU - Koychev, Ivan

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Given the constantly growing proliferation of false claims online in recent years, there has been also a growing research interest in automatically distinguishing false rumors from factually true claims. Here, we propose a general-purpose framework for fully-automatic fact checking using external sources, tapping the potential of the entire Web as a knowledge source to confirm or reject a claim. Our framework uses a deep neural network with LSTM text encoding to combine semantic kernels with task-specific embeddings that encode a claim together with pieces of potentially-relevant text fragments from the Web, taking the source reliability into account. The evaluation results show good performance on two different tasks and datasets: (i) rumor detection and (if) fact checking of the answers to a question in community question answering forums.

AB - Given the constantly growing proliferation of false claims online in recent years, there has been also a growing research interest in automatically distinguishing false rumors from factually true claims. Here, we propose a general-purpose framework for fully-automatic fact checking using external sources, tapping the potential of the entire Web as a knowledge source to confirm or reject a claim. Our framework uses a deep neural network with LSTM text encoding to combine semantic kernels with task-specific embeddings that encode a claim together with pieces of potentially-relevant text fragments from the Web, taking the source reliability into account. The evaluation results show good performance on two different tasks and datasets: (i) rumor detection and (if) fact checking of the answers to a question in community question answering forums.

UR - http://www.scopus.com/inward/record.url?scp=85045722270&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045722270&partnerID=8YFLogxK

U2 - 10.26615/978-954-452-049-6-046

DO - 10.26615/978-954-452-049-6-046

M3 - Conference contribution

VL - 2017-September

SP - 344

EP - 353

BT - International Conference on Recent Advances in Natural Language Processing

PB - Association for Computational Linguistics (ACL)

ER -