Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing |
| Seiten | 1583-1595 |
| Seitenumfang | 13 |
| Publikationsstatus | Veröffentlicht - 2021 |
| Extern publiziert | Ja |
| Veranstaltung | Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021 - Virtual, Online Dauer: 1 Aug. 2021 → 6 Aug. 2021 |
Abstract
Approaches to computational argumentation tasks such as stance detection and aspect detection have largely focused on the text of individual claims, losing out on potentially valuable context from the broader collection of text. We present a general approach to these tasks motivated by syntopical reading, a reading process that emphasizes comparing and contrasting viewpoints in order to improve topic understanding. To capture collection-level context, we introduce the syntopical graph, a data structure for linking claims within a collection. A syntopical graph is a typed multi-graph where nodes represent claims and edges represent different possible pairwise relationships, such as entailment, paraphrase, or support. Experiments applying syntopical graphs to stance detection and aspect detection demonstrate state-of-the-art performance in each domain, significantly outperforming approaches that do not utilize collection-level information.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Software
- Informatik (insg.)
- Theoretische Informatik und Mathematik
- Sozialwissenschaften (insg.)
- Linguistik und Sprache
- Geisteswissenschaftliche Fächer (insg.)
- Sprache und Linguistik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 2021. S. 1583-1595.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Syntopical graphs for computational argumentation tasks
AU - Barrow, Joe
AU - Jain, Rajiv
AU - Lipka, Nedim
AU - Dernoncourt, Franck
AU - Morariu, Vlad I.
AU - Manjunatha, Varun
AU - Oard, Douglas W.
AU - Resnik, Philip
AU - Wachsmuth, Henning
N1 - Funding Information: We would like to thank many others for their invaluable feedback and patient discussions, including Charlotte Ellison, Ani Nenkova, Tong Sun, Han-Chin Shing, and Pedro Rodriguez. This work was generously supported through Adobe Gift Funding, which supports an Adobe Research-University of Maryland collaboration. It was completed while the primary author was interning at Adobe Research.
PY - 2021
Y1 - 2021
N2 - Approaches to computational argumentation tasks such as stance detection and aspect detection have largely focused on the text of individual claims, losing out on potentially valuable context from the broader collection of text. We present a general approach to these tasks motivated by syntopical reading, a reading process that emphasizes comparing and contrasting viewpoints in order to improve topic understanding. To capture collection-level context, we introduce the syntopical graph, a data structure for linking claims within a collection. A syntopical graph is a typed multi-graph where nodes represent claims and edges represent different possible pairwise relationships, such as entailment, paraphrase, or support. Experiments applying syntopical graphs to stance detection and aspect detection demonstrate state-of-the-art performance in each domain, significantly outperforming approaches that do not utilize collection-level information.
AB - Approaches to computational argumentation tasks such as stance detection and aspect detection have largely focused on the text of individual claims, losing out on potentially valuable context from the broader collection of text. We present a general approach to these tasks motivated by syntopical reading, a reading process that emphasizes comparing and contrasting viewpoints in order to improve topic understanding. To capture collection-level context, we introduce the syntopical graph, a data structure for linking claims within a collection. A syntopical graph is a typed multi-graph where nodes represent claims and edges represent different possible pairwise relationships, such as entailment, paraphrase, or support. Experiments applying syntopical graphs to stance detection and aspect detection demonstrate state-of-the-art performance in each domain, significantly outperforming approaches that do not utilize collection-level information.
UR - http://www.scopus.com/inward/record.url?scp=85118920064&partnerID=8YFLogxK
U2 - 10.18653/v1/2021.acl-long.126
DO - 10.18653/v1/2021.acl-long.126
M3 - Conference contribution
AN - SCOPUS:85118920064
SN - 9781954085527
SP - 1583
EP - 1595
BT - Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
T2 - Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021
Y2 - 1 August 2021 through 6 August 2021
ER -