Title | ||
---|---|---|
An alternative to head-driven approaches for parsing a (relatively) free word-order language |
Abstract | ||
---|---|---|
Applying statistical parsers developed for English to languages with freer word-order has turned out to be harder than expected. This paper investigates the adequacy of different statistical parsing models for dealing with a (relatively) free word-order language. We show that the recently proposed Relational-Realizational (RR) model consistently outperforms state-of-the-art Head-Driven (HD) models on the Hebrew Treebank. Our analysis reveals a weakness of HD models: their intrinsic focus on configurational information. We conclude that the form-function separation ingrained in RR models makes them better suited for parsing nonconfigurational phenomena. |
Year | Venue | Keywords |
---|---|---|
2009 | Basic and Applied Ecology | configurational information,rr model,hd model,hebrew treebank,form-function separation,intrinsic focus,different statistical parsing model,free word-order language,statistical parsers,freer word-order |
Field | DocType | Volume |
Word order,Computer science,Hebrew,Speech recognition,Artificial intelligence,Treebank,Natural language processing,Statistical parsing,Parsing,Machine learning | Conference | D09-1 |
Citations | PageRank | References |
4 | 0.46 | 12 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Reut Tsarfaty | 1 | 230 | 24.59 |
Khalil Sima'an | 2 | 443 | 50.32 |
Remko Scha | 3 | 134 | 47.62 |