Data from the Paper: Entities as Topic Labels - Combining Entity Linking and Labeled LDA to Improve Topic Interpretability and Evaluability.

Item Type:	Dataset
Title:	Data from the Paper: Entities as Topic Labels - Combining Entity Linking and Labeled LDA to Improve Topic Interpretability and Evaluability.
Date:	2016
Creator:	Lauscher, Anne, Nanni, Federico, Ruiz Fabo, Pablo and Ponzetto, Simone Paolo
Divisions:	Außerfakultäre Einrichtungen > SFB 884 School of Business Informatics and Mathematics > Semantic Web (Juniorprofessur) (Ponzetto 2013-15)

DDC Classification:

004 Computer science, internet

Abstract:

Digital humanities scholars strongly need a corpus exploration method that provides topics easier to interpret than standard LDA topic models. To move towards this goal, here we propose a combination of two techniques, called Entity Linking and Labeled LDA. Our method identifies in an ontology a series of descriptive labels for each document in a corpus. Then it generates a specific topic for each label. Having a direct relation between topics and labels makes interpretation easier; using an ontology as background knowledge limits label ambiguity. As our topics are described with a limited number of clear-cut labels, they promote interpretability and support the quantitative evaluation of the obtained results. We illustrate the potential of the approach by applying it to three datasets, namely the transcription of speeches from the European Parliament fifth mandate, the Enron Corpus and the Hillary Clinton Email Dataset. While some of these resources have already been adopted by the natural language processing community, they still hold a large potential for humanities scholars, part of which could be exploited in studies that will adopt the fine-grained exploration method presented in this paper.

URL:	https://madata.bib.uni-mannheim.de/238/
DOI:	https://doi.org/10.7801/238
Availability (Controlled):	Unknown
Publication(s) (MADOC):	Lauscher Anne und Nanni Federico und Ruiz Fabo Pablo und Ponzetto Simone Paolo (2016), Entities as topic labels : combining entity linking and labeled LDA to improve topic interpretability and evaluability

Metadata export

EP3 XMLMultiline CSVBibTeXHTML CitationReference Manager

File	Filename / Infos	Link
	Text Filename: readme.txt	Download (910B)
	Text Filename: europarl.sql	Download (89MB)
	Text Filename: enron.sql	Download (34MB)
	Text Filename: clinton.sql	Download (50MB)

Depositing User:	Anne Ruth Lauscher
Date Deposited:	12 Sep 2017 07:39
Last Modified:	29 Feb 2024 20:09

Actions (login required)

View Item