Name
Abstract | ||
|---|---|---|
We present an algorithm for generating referring expressions in open domains. Existing algorithms work at the semantic level and assume the availability of a classification for attributes, which is only feasible for restricted domains. Our alternative works at the realisation level, relies on Word-Net synonym and antonym sets, and gives equivalent results on the examples cited in the literature and improved results for examples that prior approaches cannot handle. We believe that ours is also the first algorithm that allows for the incremental incorporation of relations. We present a novel corpus-evaluation using referring expressions from the Penn Wall Street Journal Treebank. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.3115/1218955.1219007 | ACL |
Keywords | Field | DocType |
incremental incorporation,alternative work,improved result,open domain,word-net synonym,antonym set,realisation level,equivalent result,algorithms work,penn wall street journal,semantic level,computer science,information technology | Expression (mathematics),Information technology,Computer science,Realisation,Treebank,Natural language processing,Artificial intelligence | Conference |
Volume | Citations | PageRank |
P04-1 | 21 | 1.21 |
References | Authors | |
9 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Advaith Siddharthan | 1 | 379 | 33.28 |
| Ann Copestake | 2 | 862 | 95.10 |