Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

12

ACL
2000

favoriteEmaildiscussreport

127views Computational Linguistics» more ACL 2000»

Statistical Parsing with an Automatically-Extracted Tree Adjoining Grammar

13 years 5 months ago

Statistical Parsing with an Automatically-Extracted Tree Adjoining Grammar

Download acl.ldc.upenn.edu

We discuss the advantages of lexicalized tree-adjoining grammar as an alternative to lexicalized PCFG for statistical parsing, describingthe induction of a probabilistic LTAG model from the Penn Treebank and evaluating its parsing performance. We nd that this induction method is an improvement over the EM-based method of Hwa, 1998, and that the induced model yields results comparable to lexicalized PCFG.

David Chiang

Real-time Traffic

ACL 2000 | ACL 2007 | Lexicalized | Probabilistic Ltag Model | Statistical Parsing |

claim paper

Related Content

» XTAG System A Wide Coverage Grammar for English

» Automatically Extracting and Comparing Lexicalized Grammars for Different Languages

» Tabulation of Automata for TreeAdjoining Languages

» Bidirectional Automata for Tree Adjoining Grammars

» The Use of Shared Forests in Tree Adjoining Grammar Parsing

» Incremental Parser Generation for Tree Adjoining Grammars

» Deterministic Left to Right Parsing of Tree Adjoining Languages

» Another Facet of LIG Parsing

» A Symbolic Approach to NearDeterministic Surface Realisation using Tree Adjoining Grammar

Post Info
More Details (n/a)

Added	01 Nov 2010
Updated	01 Nov 2010
Type	Conference
Year	2000
Where	ACL
Authors	David Chiang

Comments (0)