Paper: Content Importance Models for Scoring Writing From Sources

ACL ID P14-2041
Title Content Importance Models for Scoring Writing From Sources
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Selection of information from external sources is an important skill assessed in educational measurement. We address an integrative summarization task used in an assessment of English proficiency for non- native speakers applying to higher educa- tion institutions in the USA. We evaluate a variety of content importance models that help predict which parts of the source ma- terial should be selected by the test-taker in order to succeed on this task.