Title | ||
---|---|---|
Referring expression generation using speaker-based attribute selection and trainable realization (ATTR) |
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 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. |
Year | Venue | Keywords |
---|---|---|
2008 | International Conference on Natural Language Generation | speaker-based attribute selection,attribute selection,word order information,consideration speaker style,stylistic difference,expression generation,reg competition,data-driven surface realization technique,general-purpose algorithm,trainable surface realization approach,trainable realization,expression generation algorithm |
Field | DocType | Citations |
Referring expression generation,Word order,Feature selection,Computer science,Speech recognition,Natural language processing,Artificial intelligence | Conference | 8 |
PageRank | References | Authors |
0.63 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Giuseppe Di Fabbrizio | 1 | 330 | 44.45 |
Amanda J. Stent | 2 | 1094 | 103.35 |
Srinivas Bangalore | 3 | 1319 | 157.37 |