Abstract | ||
---|---|---|
We show that naïve modeling of morphosyn-tactic agreement in a Constituency-Based (CB) statistical parsing model is worse than none, whereas a linguistically adequate way of modeling inflectional morphology in CB parsing leads to improved performance. In particular, we show that an extension of the Relational-Realizational (RR) model that incorporates agreement features is superior to CB models that treat morphosyntax as state-splits (SP), and that the RR model benefits more from inflectional features. We focus on parsing Hebrew and report the best result to date, F184.13 for parsing off of gold-tagged text, 5% error reduction from previous results. |
Year | Venue | Keywords |
---|---|---|
2010 | SPMRL@NAACL-HLT | modern hebrew,statistical parsing model,agreement feature,rr model benefit,inflectional morphology,morphosyntactic agreement,best result,cb model,constituency-based parsing,morphosyn-tactic agreement,cb parsing,inflectional feature,parsing hebrew |
Field | DocType | Citations |
Computer science,Hebrew,Speech recognition,Artificial intelligence,Natural language processing,Statistical parsing,Parsing | Conference | 8 |
PageRank | References | Authors |
0.51 | 8 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Reut Tsarfaty | 1 | 230 | 24.59 |
Khalil Sima'an | 2 | 443 | 50.32 |