Mining arguments in scientific abstracts with discourse-level embeddings

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Accuosto, Pablo
• dc.contributor.author Saggion, Horacio
• dc.date.accessioned 2020-08-27T09:01:25Z
• dc.date.issued 2020
• dc.description.abstract Argument mining consists in the automatic identification of argumentative structures in texts. In this work we leverage existing discourse-level annotations to facilitate the identification of argumentative components and relations in scientific texts, which has been recognized as a particularly challenging task. We propose a new annotation schema and use it to augment a corpus of computational linguistics abstracts that had previously been annotated with discourse units and relations. Our initial experiments with the enriched corpus confirm the potential value of incorporating discourse information in argument mining tasks. In order to tackle the limitations posed by the lack of corpora containing both discourse and argumentative annotations we explore two transfer learning approaches in which discourse parsing is used as an auxiliary task when training argument mining models. In this case, as no discourse information is used as input, the resulting models could be used to predict the argumentative structure of unannotated texts.
• dc.description.sponsorship This work is (partly) supported by the Spanish Government under the María de Maeztu Units of Excellence Programme (MDM-2015-0502) and the Research and Innovation Agency of Uruguay (ANII).
• dc.description.sponsorship This work is (partly) supported by the Spanish Government under the Mar´ıa de Maeztu Units of Excellence Programme (MDM-2015-0502) and the Research and Innovation Agency of Uruguay (ANII).
• dc.format.mimetype application/pdf
• dc.identifier.citation Accuosto P, Saggion H. Mining arguments in scientific abstracts with discourse-level embeddings. Data Knowl Eng. 2020;129:101840. DOI: 10.1016/j.datak.2020.101840
• dc.identifier.doi http://dx.doi.org/10.1016/j.datak.2020.101840
• dc.identifier.issn 0169-023X
• dc.identifier.uri http://hdl.handle.net/10230/45237
• dc.language.iso eng
• dc.publisher Elsevier
• dc.relation.ispartof Data & Knowledge Engineering. 2020;129:101840.
• dc.rights © Elsevier http://dx.doi.org/10.1016/j.datak.2020.101840
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.title Mining arguments in scientific abstracts with discourse-level embeddings
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/acceptedVersion