Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
Recolector de Ciencia Abierta, RECOLECTA
Doctoral thesis . 2021
License: CC BY NC SA
DBLP
Doctoral thesis . 2025
Data sources: DBLP
versions View all 3 versions
addClaim

Mining arguments in scientific abstracts: Application to argumentative quality assessment

Authors: Pablo Accuosto;

Mining arguments in scientific abstracts: Application to argumentative quality assessment

Abstract

La mineria d’arguments consisteix en la identificació automàtica d’estructures argumentatives en el llenguatge natural, una tasca considerada com a especialment complexa en textos científics. En aquest treball proposem SciARG, un nou esquema d’anotació, i l’apliquem a la identificació d’unitats i relacions argumentatives en resums científics en dues disciplines: lingüística computacional i biomedicina, la qual cosa ens permet avaluar l’aplicabilitat del nostre esquema en diferents camps del coneixement. Utilitzem el nostre corpus per entrenar i avaluar models de mineria d’arguments en diversos contextos experimentals, entrenant cada tasca per separat i en un entorn multitasca. Investiguem la possibilitat d’aprofitar anotacions existents, incloent relacions de discurs i funcions retòriques d’oracions, per millorar el rendiment dels models de mineria de arguments. En particular, explorem el potencial que ofereix un enfocament d’aprenentatge per transferència en el qual s’utilitzen tasques d’entrenament suplementàries per afinar models lingüístics pre-entrenats. Finalment, analitzem l’´us pràctic dels components i relacions extretes automàticament dels textos per la predicció de diversos aspectes de la qualitat argumentativa de resums científics.

Argument mining consists in the automatic identification of argumentative structures in natural language, a task that has been recognized as particularly challenging in the scientific domain. In this work we propose SciARG, a new annotation scheme, and apply it to the identification of argumentative units and relations in abstracts in two scientific disciplines: computational linguistics and biomedicine, which allows us to assess the applicability of our scheme to different knowledge fields. We use our annotated corpus to train and evaluate argument mining models in various experimental settings, including single and multi-task learning. We investigate the possibility of leveraging existing annotations, including discourse relations and rhetorical roles of sentences, to improve the performance of argument mining models. In particular, we explore the potential offered by a sequential transfer-learning approach in which supplementary training tasks are used to fine-tune pre-trained parameter-rich language models. Finally, we analyze the practical usability of the automatically-extracted components and relations for the prediction of argumentative quality dimensions of scientific abstracts.

Programa de doctorat en Tecnologies de la Informació i les Comunicacions

Keywords

62, Scientific discourse, Argumentative quality assessment, Avaluació de la qualitat argumentativa, Esquema d’anotacions, Aprenentatge per transferència, Scholarly publications, Transfer learning, Argument meaning, Machine learning, Aprenentatge automàtic, Mineria d’arguments, Annotation scheme, Publicacions acadèmiques, Discurs científic, BERT

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green