CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Extractive Summarization using Continuous Vector Space Models

Mikael Kågebäck (Institutionen för data- och informationsteknik, Datorteknik (Chalmers)) ; Olof Mogren (Institutionen för data- och informationsteknik, Datavetenskap, Algoritmer (Chalmers)) ; Nina Tahmasebi (Institutionen för data- och informationsteknik (Chalmers)) ; Devdatt Dubhashi (Institutionen för data- och informationsteknik (Chalmers))
Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC) EACL, April 26-30, 2014 Gothenburg, Sweden p. 31-39. (2014)
[Konferensbidrag, refereegranskat]

Automatic summarization can help users extract the most important pieces of information from the vast amount of text digitized into electronic form everyday. Central to automatic summarization is the notion of similarity between sentences in text. In this paper we propose the use of continuous vector representations for semantically aware representations of sentences as a basis for measuring similarity. We evaluate different compositions for sentence representation on a standard dataset using the ROUGE evaluation measures. Our experiments show that the evaluated methods improve the performance of a state-of-the-art summarization framework and strongly indicate the benefits of continuous word vector representations for automatic summarization.



Denna post skapades 2015-01-16. Senast ändrad 2015-03-02.
CPL Pubid: 210878