Reimers, Nils ; Schiller, Benjamin ; Beck, Tilman ; Daxenberger, Johannes ; Stab, Christian ; Gurevych, Iryna (2019)
Classification and Clustering of Arguments with Contextualized Word Embeddings.
57th Annual Meeting of the Association for Computational Linguistics (ACL 2019). Florence, Italy (28.07.-02.08.2019)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and cluster topic-dependent arguments, achieving impressive results on both tasks and across multiple datasets. For argument classification, we improve the state-of-the-art for the UKP Sentential Argument Mining Corpus by 20.8 percentage points and for the IBM Debater - Evidence Sentences dataset by 7.4 percentage points. For the understudied task of argument clustering, we propose a pre-training step which improves by 7.8 percentage points over strong baselines on a novel dataset, and by 12.3 percentage points for the Argument Facet Similarity (AFS) Corpus.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2019 |
| Autor(en): | Reimers, Nils ; Schiller, Benjamin ; Beck, Tilman ; Daxenberger, Johannes ; Stab, Christian ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Classification and Clustering of Arguments with Contextualized Word Embeddings |
| Sprache: | Englisch |
| Publikationsjahr: | 27 Mai 2019 |
| Verlag: | ACL |
| Buchtitel: | Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019) |
| Veranstaltungstitel: | 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019) |
| Veranstaltungsort: | Florence, Italy |
| Veranstaltungsdatum: | 28.07.-02.08.2019 |
| URL / URN: | https://www.aclweb.org/anthology/P19-1054 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and cluster topic-dependent arguments, achieving impressive results on both tasks and across multiple datasets. For argument classification, we improve the state-of-the-art for the UKP Sentential Argument Mining Corpus by 20.8 percentage points and for the IBM Debater - Evidence Sentences dataset by 7.4 percentage points. For the understudied task of argument clustering, we propose a pre-training step which improves by 7.8 percentage points over strong baselines on a novel dataset, and by 12.3 percentage points for the Argument Facet Similarity (AFS) Corpus. |
| Freie Schlagworte: | UKP_p_OAM |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Graduiertenkolleg 1994 Adaptive Informationsaufbereitung aus heterogenen Quellen |
| Hinterlegungsdatum: | 30 Okt 2019 13:55 |
| Letzte Änderung: | 16 Jul 2021 10:17 |
| PPN: | |
| Zugehörige Links: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum