Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings of the 4th Workshop on Argument Mining |
| Herausgeber/-innen | Ivan Habernal, Iryna Gurevych, Kevin Ashley, Clair Cardie, Nancy Green, Diane Litman, Georgios Petasis, Chris Reed, Noam Slonim, Vern Walker |
| Seiten | 118-128 |
| Seitenumfang | 11 |
| ISBN (elektronisch) | 9781945626845 |
| Publikationsstatus | Veröffentlicht - Sept. 2017 |
| Extern publiziert | Ja |
| Veranstaltung | EMNLP 2017 4th Workshop on Argument Mining - Copenhagen, Dänemark Dauer: 8 Sept. 2017 → 8 Sept. 2017 |
Abstract
The segmentation of an argumentative text into argument units and their nonargumentative counterparts is the first step in identifying the argumentative structure of the text. Despite its importance for argument mining, unit segmentation has been approached only sporadically so far. This paper studies the major parameters of unit segmentation systematically. We explore the effectiveness of various features, when capturing words separately, along with their neighbors, or even along with the entire text. Each such context is reflected by one machine learning model that we evaluate within and across three domains of texts. Among the models, our new deep learning approach capturing the entire text turns out best within all domains, with an F-score of up to 88.54. While structural features generalize best across domains, the domain transfer remains hard, which points to major challenges of unit segmentation.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Theoretische Informatik und Mathematik
- Informatik (insg.)
- Information systems
- Informatik (insg.)
- Angewandte Informatik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings of the 4th Workshop on Argument Mining. Hrsg. / Ivan Habernal; Iryna Gurevych; Kevin Ashley; Clair Cardie; Nancy Green; Diane Litman; Georgios Petasis; Chris Reed; Noam Slonim; Vern Walker. 2017. S. 118-128.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Unit Segmentation of Argumentative Texts
AU - Ajjour, Yamen
AU - Chen, Wei Fan
AU - Kiesel, Johannes
AU - Wachsmuth, Henning
AU - Stein, Benno
PY - 2017/9
Y1 - 2017/9
N2 - The segmentation of an argumentative text into argument units and their nonargumentative counterparts is the first step in identifying the argumentative structure of the text. Despite its importance for argument mining, unit segmentation has been approached only sporadically so far. This paper studies the major parameters of unit segmentation systematically. We explore the effectiveness of various features, when capturing words separately, along with their neighbors, or even along with the entire text. Each such context is reflected by one machine learning model that we evaluate within and across three domains of texts. Among the models, our new deep learning approach capturing the entire text turns out best within all domains, with an F-score of up to 88.54. While structural features generalize best across domains, the domain transfer remains hard, which points to major challenges of unit segmentation.
AB - The segmentation of an argumentative text into argument units and their nonargumentative counterparts is the first step in identifying the argumentative structure of the text. Despite its importance for argument mining, unit segmentation has been approached only sporadically so far. This paper studies the major parameters of unit segmentation systematically. We explore the effectiveness of various features, when capturing words separately, along with their neighbors, or even along with the entire text. Each such context is reflected by one machine learning model that we evaluate within and across three domains of texts. Among the models, our new deep learning approach capturing the entire text turns out best within all domains, with an F-score of up to 88.54. While structural features generalize best across domains, the domain transfer remains hard, which points to major challenges of unit segmentation.
UR - http://www.scopus.com/inward/record.url?scp=85072867012&partnerID=8YFLogxK
U2 - 10.18653/v1/W17-5115
DO - 10.18653/v1/W17-5115
M3 - Conference contribution
AN - SCOPUS:85072867012
SP - 118
EP - 128
BT - Proceedings of the 4th Workshop on Argument Mining
A2 - Habernal, Ivan
A2 - Gurevych, Iryna
A2 - Ashley, Kevin
A2 - Cardie, Clair
A2 - Green, Nancy
A2 - Litman, Diane
A2 - Petasis, Georgios
A2 - Reed, Chris
A2 - Slonim, Noam
A2 - Walker, Vern
T2 - EMNLP 2017 4th Workshop on Argument Mining, ArgMining 2017
Y2 - 8 September 2017 through 8 September 2017
ER -