Detecting summary-worthy sentences: the effect of discourse features

Maximilian Droog-Hayes, Geraint Wiggins, Matthew Purver

Onderzoeksoutput: Conference paper

Samenvatting

We examine the benefit of a variety of discourse and semantic features for the identification of summary-worthy content in narrative stories. Using logistic regression models, we find that the most informative features are those that relate to the narrative structure of a text. We show that automatic methods for feature extraction perform significantly worse than full manual annotation, but that with optimization, a fully automatic approach can outperform a variety of existing extractive approaches to summarization.

Originele taal-2English
TitelProceedings of the 13th IEEE International Conference on Semantic Computing (ICSC)
UitgeverijIEEE
Pagina's381-384
Aantal pagina's4
Volume13
ISBN van geprinte versie978-1-5386-6783-5
StatusPublished - 2019
Evenement13th IEEE International Conference on Semantic Computing (ICSC) - Newport Beach Mariott Bayview, Newport Beach, United States
Duur: 30 jan 20191 feb 2019
Congresnummer: 13
https://semanticcomputing.wixsite.com/icsc-2019

Conference

Conference13th IEEE International Conference on Semantic Computing (ICSC)
Verkorte titelICSC
LandUnited States
StadNewport Beach
Periode30/01/191/02/19
Internet adres

Vingerafdruk

Duik in de onderzoeksthema's van 'Detecting summary-worthy sentences: the effect of discourse features'. Samen vormen ze een unieke vingerafdruk.

Citeer dit