Paper: Automated Pyramid Scoring of Summaries using Distributional Semantics

ACL ID P13-2026
Title Automated Pyramid Scoring of Summaries using Distributional Semantics
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

The pyramid method for content evaluation of auto- mated summarizers produces scores that are shown to correlate well with manual scores used in edu- cational assessment of students? summaries. This motivates the development of a more accurate auto- mated method to compute pyramid scores. Of three methods tested here, the one that performs best re- lies on latent semantics.