The impact of modeling overall argumentation with tree kernels

Henning Wachsmuth, Giovanni Martino, Dora Kiesel, Benno Stein

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

Abstract

Several approaches have been proposed to model either the explicit sequential structure of an argumentative text or its implicit hierarchical structure. So far, the adequacy of these models of overall argumentation remains unclear. This paper asks what type of structure is actually important to tackle downstream tasks in computational argumentation. We analyze patterns in the overall argumentation of texts from three corpora. Then, we adapt the idea of positional tree kernels in order to capture sequential and hierarchical argumentative structure together for the first time. In systematic experiments for three text classification tasks, we find strong evidence for the impact of both types of structure. Our results suggest that either of them is necessary while their combination may be beneficial.

Original languageEnglish
Title of host publicationEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages2379-2389
Number of pages11
ISBN (Electronic)9781945626838
Publication statusPublished - 1 Jan 2017
Event2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 - Copenhagen, Denmark
Duration: 9 Sep 201711 Sep 2017

Publication series

NameEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
CountryDenmark
CityCopenhagen
Period9/9/1711/9/17

Fingerprint

Experiments

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computational Theory and Mathematics

Cite this

Wachsmuth, H., Martino, G., Kiesel, D., & Stein, B. (2017). The impact of modeling overall argumentation with tree kernels. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 2379-2389). (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings). Association for Computational Linguistics (ACL).

The impact of modeling overall argumentation with tree kernels. / Wachsmuth, Henning; Martino, Giovanni; Kiesel, Dora; Stein, Benno.

EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2017. p. 2379-2389 (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).

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

Wachsmuth, H, Martino, G, Kiesel, D & Stein, B 2017, The impact of modeling overall argumentation with tree kernels. in EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings, Association for Computational Linguistics (ACL), pp. 2379-2389, 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, 9/9/17.
Wachsmuth H, Martino G, Kiesel D, Stein B. The impact of modeling overall argumentation with tree kernels. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL). 2017. p. 2379-2389. (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).
Wachsmuth, Henning ; Martino, Giovanni ; Kiesel, Dora ; Stein, Benno. / The impact of modeling overall argumentation with tree kernels. EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2017. pp. 2379-2389 (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).
@inproceedings{921a468c80ea481ab2c0f94ce646e273,
title = "The impact of modeling overall argumentation with tree kernels",
abstract = "Several approaches have been proposed to model either the explicit sequential structure of an argumentative text or its implicit hierarchical structure. So far, the adequacy of these models of overall argumentation remains unclear. This paper asks what type of structure is actually important to tackle downstream tasks in computational argumentation. We analyze patterns in the overall argumentation of texts from three corpora. Then, we adapt the idea of positional tree kernels in order to capture sequential and hierarchical argumentative structure together for the first time. In systematic experiments for three text classification tasks, we find strong evidence for the impact of both types of structure. Our results suggest that either of them is necessary while their combination may be beneficial.",
author = "Henning Wachsmuth and Giovanni Martino and Dora Kiesel and Benno Stein",
year = "2017",
month = "1",
day = "1",
language = "English",
series = "EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "2379--2389",
booktitle = "EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings",

}

TY - GEN

T1 - The impact of modeling overall argumentation with tree kernels

AU - Wachsmuth, Henning

AU - Martino, Giovanni

AU - Kiesel, Dora

AU - Stein, Benno

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Several approaches have been proposed to model either the explicit sequential structure of an argumentative text or its implicit hierarchical structure. So far, the adequacy of these models of overall argumentation remains unclear. This paper asks what type of structure is actually important to tackle downstream tasks in computational argumentation. We analyze patterns in the overall argumentation of texts from three corpora. Then, we adapt the idea of positional tree kernels in order to capture sequential and hierarchical argumentative structure together for the first time. In systematic experiments for three text classification tasks, we find strong evidence for the impact of both types of structure. Our results suggest that either of them is necessary while their combination may be beneficial.

AB - Several approaches have been proposed to model either the explicit sequential structure of an argumentative text or its implicit hierarchical structure. So far, the adequacy of these models of overall argumentation remains unclear. This paper asks what type of structure is actually important to tackle downstream tasks in computational argumentation. We analyze patterns in the overall argumentation of texts from three corpora. Then, we adapt the idea of positional tree kernels in order to capture sequential and hierarchical argumentative structure together for the first time. In systematic experiments for three text classification tasks, we find strong evidence for the impact of both types of structure. Our results suggest that either of them is necessary while their combination may be beneficial.

UR - http://www.scopus.com/inward/record.url?scp=85061325760&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061325760&partnerID=8YFLogxK

M3 - Conference contribution

T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

SP - 2379

EP - 2389

BT - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

PB - Association for Computational Linguistics (ACL)

ER -