Abstract | ||
---|---|---|
This paper addresses a data-driven surface realisation model based on a large-scale reversible grammar of German. We investigate the relationship between the surface realisation performance and the character of the input to generation, i.e. its degree of underspecification. We extend a syntactic surface realisation system, which can be trained to choose among word order variants, such that the candidate set includes active and passive variants. This allows us to study the interaction of voice and word order alternations in realistic German corpus data. We show that with an appropriately underspecified input, a linguistically informed realisation model trained to regenerate strings from the underlying semantic representation achieves 91.5% accuracy (over a baseline of 82.5%) in the prediction of the original voice. |
Year | Venue | Keywords |
---|---|---|
2011 | ACL | data-driven surface realisation model,realistic german corpus data,surface realisation ranking,surface realisation performance,syntactic surface realisation system,underspecified input,realisation model,original voice,word order alternation,word order variant,candidate set |
Field | DocType | Volume |
Underspecification,Computer science,Artificial intelligence,Natural language processing,Syntax,Word order,Ranking,Speech recognition,Grammar,Realisation,Semantic representation,Machine learning,German | Conference | P11-1 |
Citations | PageRank | References |
5 | 0.49 | 20 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sina Zarrieß | 1 | 35 | 8.65 |
Aoife Cahill | 2 | 404 | 35.53 |
Jonas Kuhn | 3 | 115 | 13.05 |