Unsupervised text segmentation using semantic relatedness graphs

Glavaš, Goran ; Nanni, Federico ; Ponzetto, Simone Paolo

S16-2016.pdf - Published

Download (164kB)

URL: https://madoc.bib.uni-mannheim.de/41341
Additional URL: https://aclweb.org/anthology/S/S16/S16-2016.pdf
URN: urn:nbn:de:bsz:180-madoc-413416
Document Type: Conference or workshop publication
Year of publication: 2016
Book title: *SEM 2016: The Fifth Joint Conference on Lexical and Computational Semantics : proceedings of the conference ; August 11-12 2016, Berlin, Germany
The title of a journal, publication series: Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics
Page range: 125-130
Conference title: Fifth Joint Conference on Lexical and Computational Semantics (*SEM-2016)
Location of the conference venue: Berlin, Germany
Date of the conference: 11 August 2016
Publisher: Gardent, Claire
Place of publication: Stroudsburg, Pa.
Publishing house: Association for Computational Linguistics
ISBN: 978-1-941643-92-1
Publication language: English
Institution: School of Business Informatics and Mathematics > Information Systems III: Enterprise Data Analysis (Ponzetto 2016-)
Subject: 004 Computer science, internet
Keywords (English): text segmentation , graph cliques , natural language processing
Abstract: Segmenting text into semantically coherent fragments improves readability of text and facilitates tasks like text summarization and passage retrieval. In this paper, we present a novel unsupervised algorithm for linear text segmentation (TS) that exploits word embeddings and a measure of semantic relatedness of short texts to construct a semantic relatedness graph of the document. Semantically coherent segments are then derived from maximal cliques of the relatedness graph. The algorithm performs competitively on a standard synthetic dataset and outperforms the best-performing method on a real-world (i.e., non-artificial) dataset of political manifestos.

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