In this paper we present a new unsupervised approach, “Attraction to Topics” – A2T , for the detection of argumentative units, a sub-task of argument mining. Motivated by the importance of topic identi- fication in manual annotation, we examine whether topic modeling can be used for performing unsupervised detection of argumentative sentences, and to what extend topic modeling can be used to classify sentences as claims and premises. Preliminary evaluation results suggest that topic information can be successfully used for the detection of argumentative sentences, at least for corpora used in the evaluation. Our approach has been evaluated on two English corpora, the first of which contains 90 persuasive essays, while the second is a collection of 340 documents from user generated content.
Unsupervised Detection of Argumentative Units though Topic Modeling Techniques / A. Ferrara, S. Montanelli, G. Petasis - In: Proceedings of the 4th Workshop on Argument Mining[s.l] : Association for Computational Linguistics, 2017. - pp. 97-107 (( convegno EMNLP tenutosi a Copenhagen nel 2017.
Unsupervised Detection of Argumentative Units though Topic Modeling Techniques
A. FerraraPrimo
;S. MontanelliSecondo
;
2017
Abstract
In this paper we present a new unsupervised approach, “Attraction to Topics” – A2T , for the detection of argumentative units, a sub-task of argument mining. Motivated by the importance of topic identi- fication in manual annotation, we examine whether topic modeling can be used for performing unsupervised detection of argumentative sentences, and to what extend topic modeling can be used to classify sentences as claims and premises. Preliminary evaluation results suggest that topic information can be successfully used for the detection of argumentative sentences, at least for corpora used in the evaluation. Our approach has been evaluated on two English corpora, the first of which contains 90 persuasive essays, while the second is a collection of 340 documents from user generated content.File | Dimensione | Formato | |
---|---|---|---|
document.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
517.08 kB
Formato
Adobe PDF
|
517.08 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.