Extracting Core Claims from Scientific Articles

Tom Jansen, Tobias Kuhn

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

The number of scientific articles has grown rapidly over the years and there are no signs that this growth will slow down in the near future. Because of this, it becomes increasingly difficult to keep up with the latest developments in a scientific field. To address this problem, we present here an approach to help researchers learn about the latest developments and findings by extracting in a normalized form core claims from scientific articles. This normalized representation is a controlled natural language of English sentences called AIDA, which has been proposed in previous work as a method to formally structure and organize scientific findings and discourse. We show how such AIDA sentences can be automatically extracted by detecting the core claim of an article, checking for AIDA compliance, and - if necessary - transforming it into a compliant sentence. While our algorithm is still far from perfect, our results indicate that the different steps are feasible and they support the claim that AIDA sentences might be a promising approach to improve scientific communication in the future.
Original languageEnglish
Pages (from-to)32-46
JournalPostproceedings of the Benelux Conference on Artificial Intelligence (BNAIC) 2016
Volume2016
DOIs
Publication statusPublished - 24 Jul 2017

Fingerprint

Communication
Compliance

Bibliographical note

In Post-proceedings of the 28th Benelux Conference on Artificial Intelligence (BNAIC 2016)

Keywords

  • cs.IR
  • cs.CL
  • cs.DL

Cite this

@article{6bcb395c6438466895900d610e4e4824,
title = "Extracting Core Claims from Scientific Articles",
abstract = "The number of scientific articles has grown rapidly over the years and there are no signs that this growth will slow down in the near future. Because of this, it becomes increasingly difficult to keep up with the latest developments in a scientific field. To address this problem, we present here an approach to help researchers learn about the latest developments and findings by extracting in a normalized form core claims from scientific articles. This normalized representation is a controlled natural language of English sentences called AIDA, which has been proposed in previous work as a method to formally structure and organize scientific findings and discourse. We show how such AIDA sentences can be automatically extracted by detecting the core claim of an article, checking for AIDA compliance, and - if necessary - transforming it into a compliant sentence. While our algorithm is still far from perfect, our results indicate that the different steps are feasible and they support the claim that AIDA sentences might be a promising approach to improve scientific communication in the future.",
keywords = "cs.IR, cs.CL, cs.DL",
author = "Tom Jansen and Tobias Kuhn",
note = "In Post-proceedings of the 28th Benelux Conference on Artificial Intelligence (BNAIC 2016)",
year = "2017",
month = "7",
day = "24",
doi = "10.1007/978-3-319-67468-1_3",
language = "English",
volume = "2016",
pages = "32--46",
journal = "Postproceedings of the Benelux Conference on Artificial Intelligence (BNAIC) 2016",

}

Extracting Core Claims from Scientific Articles. / Jansen, Tom; Kuhn, Tobias.

In: Postproceedings of the Benelux Conference on Artificial Intelligence (BNAIC) 2016, Vol. 2016, 24.07.2017, p. 32-46.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Extracting Core Claims from Scientific Articles

AU - Jansen, Tom

AU - Kuhn, Tobias

N1 - In Post-proceedings of the 28th Benelux Conference on Artificial Intelligence (BNAIC 2016)

PY - 2017/7/24

Y1 - 2017/7/24

N2 - The number of scientific articles has grown rapidly over the years and there are no signs that this growth will slow down in the near future. Because of this, it becomes increasingly difficult to keep up with the latest developments in a scientific field. To address this problem, we present here an approach to help researchers learn about the latest developments and findings by extracting in a normalized form core claims from scientific articles. This normalized representation is a controlled natural language of English sentences called AIDA, which has been proposed in previous work as a method to formally structure and organize scientific findings and discourse. We show how such AIDA sentences can be automatically extracted by detecting the core claim of an article, checking for AIDA compliance, and - if necessary - transforming it into a compliant sentence. While our algorithm is still far from perfect, our results indicate that the different steps are feasible and they support the claim that AIDA sentences might be a promising approach to improve scientific communication in the future.

AB - The number of scientific articles has grown rapidly over the years and there are no signs that this growth will slow down in the near future. Because of this, it becomes increasingly difficult to keep up with the latest developments in a scientific field. To address this problem, we present here an approach to help researchers learn about the latest developments and findings by extracting in a normalized form core claims from scientific articles. This normalized representation is a controlled natural language of English sentences called AIDA, which has been proposed in previous work as a method to formally structure and organize scientific findings and discourse. We show how such AIDA sentences can be automatically extracted by detecting the core claim of an article, checking for AIDA compliance, and - if necessary - transforming it into a compliant sentence. While our algorithm is still far from perfect, our results indicate that the different steps are feasible and they support the claim that AIDA sentences might be a promising approach to improve scientific communication in the future.

KW - cs.IR

KW - cs.CL

KW - cs.DL

U2 - 10.1007/978-3-319-67468-1_3

DO - 10.1007/978-3-319-67468-1_3

M3 - Article

VL - 2016

SP - 32

EP - 46

JO - Postproceedings of the Benelux Conference on Artificial Intelligence (BNAIC) 2016

JF - Postproceedings of the Benelux Conference on Artificial Intelligence (BNAIC) 2016

ER -