emnlp15-dim4auc

This repository contains the code used to perform the classification experiments described in section 4.2 of our EMNLP15 paper. Please use the following citation:

@inproceedings{ecklekohlerEtalEMNLP15,
	author = {Judith Eckle-Kohler and Roland Kluge and Iryna Gurevych},
	title = {On the Role of Discourse Markers for Discriminating Claims and Premises in
Argumentative Discourse},
	month = sep,
	year = {2015},
	publisher = {Association for Computational Linguistics},
	address = {Lisbon, Portugal},
	booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language
Processing (EMNLP)},
	pages = {2249-2255},
 url = {http://aclweb.org/anthology/D/D15/D15-1267.pdf}
}

Abstract: This paper presents a study on the role of discourse markers in argumentative discourse. We annotated a German corpus with arguments according to the common claim-premise model of argumentation and performed various statistical analyses regarding the discriminative nature of discourse markers for claims and premises. Our experiments show that particular semantic groups of discourse markers are indicative of either claims or premises and constitute highly predictive features for discriminating between them.

Contact person: Dr. Judith Eckle-Kohler, [email protected]

http://www.ukp.tu-darmstadt.de/

http://www.tu-darmstadt.de/

Don't hesitate to send us an e-mail or report an issue, if something is broken (and it shouldn't be) or if you have further questions.

This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication.

Project structure

• the package experiment contains the runnable classification experiments which make use of the DKPro TC framework.
• the package explore contains code used for the extraction of data-driven features from the German Tiger corpus. It makes use of DKPro Core.
• to obtain the annotated dataset, please contact [email protected] or the primary contact of the argumentation mining group at UKP, see https://www.ukp.tu-darmstadt.de/research/research-areas/argumentation-mining

Requirements

• Java 1.7 and higher
• Maven
• tested on 64-bit Linux versions and Windows 7
• recommended: 16 GB RAM

Running the experiments

• runnable classification experiments are in the package experiment; in order to run them, you have to modify the paths to corpus data and results data according to your system and environment