Automated Pyramid Scoring of Summaries using Distributional Semantics
Rebecca J. Passonneau, Emily Chen, Weiwei Guo, Dolores Perin · 2013
The pyramid method for content evaluation of automated summarizers produces scores that are shown to correlate well with manual scores used in educational assessment of students ’ summaries. This motivates the development of a more accurate automated method to compute pyramid scores. Of three methods tested here, the one that performs best relies on latent semantics. 1