Publication View

Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation (2008)

Abstract

We address the issue of human subjectivity when authoring summaries, aiming at a simple, robust evaluation of machine generated summaries. Applying a cross comprehension test on human authored short summaries from broadcast news, the level of subjectivity is gauged among four authors. The instruction set is simple, thus there is enough room for subjectivity.

Publication details

Download	http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.8069
Source	http://acl.ldc.upenn.edu/W/W05/W05-0902.pdf
Contributors	CiteSeerX
Repository	CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type	text
Language	English
Relation	10.1.1.19.9416, 10.1.1.14.1751, 10.1.1.41.1161, 10.1.1.50.2490, 10.1.1.12.4679, 10.1.1.38.8395, 10.1.1.13.489, 10.1.1.109.5097, 10.1.1.13.3858, 10.1.1.21.1535, 10.1.1.49.7094, 10.1.1.88.7264, 10.1.1.59.2145, 10.1.1.96.7987, 10.1.1.87.5199, 10.1.1.55.4054, 10.1.1.3.5936, 10.1.1.66.2737