Paper: Referring Expression Generation Using Speaker-based Attribute Selection and Trainable Realization (ATTR)

ACL ID W08-1133
Title Referring Expression Generation Using Speaker-based Attribute Selection and Trainable Realization (ATTR)
Venue International Conference on Natural Language Generation
Session Main Conference
Year 2008
Authors

In the first REG competition, researchers proposed several general-purpose algorithms for attribute selection for referring expression generation. However, most of this work did not take into account: a) stylistic differences between speakers; or b) trainable surface re- alization approaches that combine semantic and word order information. In this paper we describe and evaluate several end-to-end re- ferring expression generation algorithms that take into consideration speaker style and use data-driven surface realization techniques.