Entities as topic labels : improving topic interpretability and evaluability combining Entity Linking and Labeled LDA

Nanni, Federico ; Ruiz Fabo, Pablo

dh2016_abstracts (1).pdf - Published

Download (642kB)

URL: https://ub-madoc.bib.uni-mannheim.de/42223
Additional URL: http://dh2016.adho.org/abstracts/194
URN: urn:nbn:de:bsz:180-madoc-422233
Document Type: Conference or workshop publication
Year of publication: 2016
Book title: Digital Humanities 2016 Conference Abstracts
Page range: 632-635
Conference title: DH16, Digital Humanities 2016
Location of the conference venue: Kraków, Poland
Date of the conference: 11.-16. July, 2016
Publisher: Nanni, Federico
Place of publication: Kraków
Publishing house: Jagiellonian University & Pedagogical University
ISBN: 978–83–942760–3–4
Publication language: English
Institution: School of Business Informatics and Mathematics > Information Systems III: Enterprise Data Analysis (Ponzetto 2016-)
Subject: 004 Computer science, internet
Abstract: In order to create a corpus exploration method providing topics that are easier to interpret than standard LDA topic models, here we propose combining 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 this may help quantitative evaluation. We illustrate the potential of the approach by applying it in order to define the most relevant topics addressed by each party in the European Parliament's fifth mandate (1999-2004).

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.

Metadata export


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item