Name
Abstract | ||
|---|---|---|
In this paper, we propose a modular cascaded approach to data driven dependency parsing. Each module or layer leading to the complete parse produces a linguistically valid partial parse. We do this by introducing an artificial root node in the dependency structure of a sentence and by catering to distinct dependency label sets that reflect the function of the set internal labels vis-a¿-vis a distinct and identifiable linguistic unit, at different layers. The linguistic unit in our approach is a clause. Output (partial parse) from each layer can be accessed independently. We applied this approach to Hindi, a morphologically rich free word order language using MST parser. We did all our experiments on a part of Hyderabad Dependency Treebank. The final results show an increase of 1.35% in unlabeled attachment and 1.36% in labeled attachment accuracies over state-of-the-art data driven Hindi parser. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/IALP.2009.37 | Singapore |
Keywords | Field | DocType |
linguistically valid partial parse,dependency parsing,complete parse,modular cascaded approach,dependency structure,distinct dependency label set,attachment accuracy,partial parse,complete parsing,different layer,hindi parser,natural language processing,data mining,word order,gold,feature extraction,object recognition,grammars,accuracy,linguistics | Rule-based machine translation,Top-down parsing,Computer science,Dependency grammar,Speech recognition,Artificial intelligence,Natural language processing,Treebank,Parser combinator,Modular design,Parsing,Sentence | Conference |
ISSN | ISBN | Citations |
2159-1962 | 978-0-7695-3904-1 | 7 |
PageRank | References | Authors |
0.72 | 9 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Samar Husain | 1 | 190 | 18.43 |
| Phani Gadde | 2 | 23 | 2.56 |
| Bharat Ram Ambati | 3 | 91 | 9.55 |
| Dipti Misra Sharma | 4 | 262 | 45.90 |
| Rajeev Sangal | 5 | 220 | 33.27 |