Abstract | ||
---|---|---|
There has been a contemporary surge of interest in the application of stochastic models of parsing. The use of tree-adjoining grammar (TAG) in this domain has been relatively limited due in part to the unavailability, until recently, of large-scale corpora hand-annotated with TAG structures. Our goals are to develop inexpensive means of generating such corpora and to demonstrate their applicability to stochastic modeling. We present a method for automatically extracting a linguistically plausible TAG from the Penn Treebank. Furthermore, we also introduce labor-inexpensive methods for inducing higher-level organization of TAGs. Empirically, we perform an evaluation of various automatically extracted TAGs and also demonstrate how our induced higher-level organization of TAGs can be used for smoothing stochastic TAG models. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1017/S1351324905003943 | Natural Language Engineering |
Keywords | Field | DocType |
higher-level organization,penn treebank,linguistically plausible tag,automated extraction,contemporary surge,tag structure,induced higher-level organization,stochastic tag model,labor-inexpensive method,stochastic model,inexpensive mean,tree-adjoining grammars,tree adjoining grammar | Rule-based machine translation,Computer science,Grammar,Smoothing,Unavailability,Natural language processing,Artificial intelligence,Treebank,Stochastic modelling,Parsing | Journal |
Volume | Issue | Citations |
12 | 3 | 15 |
PageRank | References | Authors |
0.90 | 32 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
john chen | 1 | 197 | 26.31 |
Srinivas Bangalore | 2 | 1319 | 157.37 |
K. Vijay-Shanker | 3 | 2057 | 192.47 |