Paper: Extractive Summarization using Continuous Vector Space Models

ACL ID W14-1504
Title Extractive Summarization using Continuous Vector Space Models
Venue Continuous Vector Space Models and their Compositionality
Session
Year 2014
Authors

Automatic summarization can help users extract the most important pieces of infor- mation from the vast amount of text digi- tized into electronic form everyday. Cen- tral to automatic summarization is the no- tion of similarity between sentences in text. In this paper we propose the use of continuous vector representations for se- mantically aware representations of sen- tences as a basis for measuring similar- ity. We evaluate different compositions for sentence representation on a standard dataset using the ROUGE evaluation mea- sures. Our experiments show that the eval- uated methods improve the performance of a state-of-the-art summarization frame- work and strongly indicate the benefits of continuous word vector representations for automatic summarization.