Summary of the paper
| Title | Exploring the Spinal-STIG Model for Parsing French |
|---|---|
| Authors | Djamé Seddah |
| Abstract | We evaluate statistical parsing of French using two probabilistic modelsderived from the Tree Adjoining Grammar framework: a Stochastic Tree InsertionGrammars model (STIG) and a specific instance of this formalism, called SpinalTree Insertion Grammar model which exhibits interesting properties with regardto data sparseness issues common to small treebanks such as the Paris 7 FrenchTreebank. Using David Chiang’s STIG parser (Chiang, 2003), we present resultsof various experiments we conducted to explore those models for Frenchparsing. The grammar induction makes use of a head percolation table tailoredfor the French Treebank and which is provided in this paper. Using twoevaluation metrics, we found that the parsing performance of a STIG model istied to the size of the underlying Tree Insertion Grammar, with a more compactgrammar, a spinal STIG, outperforming a genuine STIG. We finally note that a"spinal" frameworkseems to emerge in the literature. Indeed, the use of vertical grammars suchas Spinal STIG instead of horizontal grammars such as PCFGs, afflicted withwellknown data sparseness issues, seems to be a promising path toward betterparsing performance. |
| Language | |
| Topics | Parsing, Grammar and Syntax |
Full paper  |
Exploring the Spinal-STIG Model for Parsing French |
| Bibtex | @InProceedings{SEDDAH10.775, author = {Djamé Seddah}, title = {Exploring the Spinal-STIG Model for Parsing French}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |