Stab, Christian ; Miller, Tristan ; Schiller, Benjamin ; Rai, Pranav ; Gurevych, Iryna (2018)
Cross-topic Argument Mining from Heterogeneous Sources.
The 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium (31.10.2018--04.11.2018)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches are designed for use only with specific text types and fall short when applied to heterogeneous texts. In this paper, we propose a new sentential annotation scheme that is reliably applicable by crowd workers to arbitrary Web texts. We source annotations for over 25,000 instances covering eight controversial topics. We show that integrating topic information into bidirectional long short-term memory networks outperforms vanilla BiLSTMs by more than 3 percentage points in F1 in two- and three-label cross-topic settings. We also show that these results can be further improved by leveraging additional data for topic relevance using multi-task learning.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2018 |
| Autor(en): | Stab, Christian ; Miller, Tristan ; Schiller, Benjamin ; Rai, Pranav ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Cross-topic Argument Mining from Heterogeneous Sources |
| Sprache: | Englisch |
| Publikationsjahr: | 4 November 2018 |
| Buchtitel: | Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing |
| Band einer Reihe: | Long Papers |
| Veranstaltungstitel: | The 2018 Conference on Empirical Methods in Natural Language Processing |
| Veranstaltungsort: | Brussels, Belgium |
| Veranstaltungsdatum: | 31.10.2018--04.11.2018 |
| URL / URN: | http://aclweb.org/anthology/D18-1402 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches are designed for use only with specific text types and fall short when applied to heterogeneous texts. In this paper, we propose a new sentential annotation scheme that is reliably applicable by crowd workers to arbitrary Web texts. We source annotations for over 25,000 instances covering eight controversial topics. We show that integrating topic information into bidirectional long short-term memory networks outperforms vanilla BiLSTMs by more than 3 percentage points in F1 in two- and three-label cross-topic settings. We also show that these results can be further improved by leveraging additional data for topic relevance using multi-task learning. |
| Freie Schlagworte: | UKP_p_ArgumenText, UKP_a_ArMin |
| ID-Nummer: | TUD-CS-2018-0052 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Graduiertenkolleg 1994 Adaptive Informationsaufbereitung aus heterogenen Quellen |
| Hinterlegungsdatum: | 08 Mär 2018 15:30 |
| Letzte Änderung: | 24 Jan 2020 12:03 |
| PPN: | |
| Zugehörige Links: | |
| Projekte: | ArgumenText |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum