Referring expression generation using speaker-based attribute selection and trainable realization (ATTR)

  • Authors:
  • Giuseppe Di Fabbrizio;Amanda J. Stent;Srinivas Bangalore

  • Affiliations:
  • AT&T Labs - Research, Inc., Florham Park, NJ;AT&T Labs - Research, Inc., Florham Park, NJ;AT&T Labs - Research, Inc., Florham Park, NJ

  • Venue:
  • INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

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 realization approaches that combine semantic and word order information. In this paper we describe and evaluate several end-to-end referring expression generation algorithms that take into consideration speaker style and use data-driven surface realization techniques.