Title | ||
---|---|---|
Chinese dependency parsing with large scale automatically constructed case structures |
Abstract | ||
---|---|---|
This paper proposes an approach using large scale case structures, which are automatically constructed from both a small tagged corpus and a large raw corpus, to improve Chinese dependency parsing. The case structure proposed in this paper has two characteristics: (1) it relaxes the predicate of a case structure to be all types of words which behaves as a head; (2) it is not categorized by semantic roles but marked by the neighboring modifiers attached to a head. Experimental results based on Penn Chinese Treebank show the proposed approach achieved 87.26% on unlabeled attachment score, which significantly outperformed the baseline parser without using case structures. |
Year | Venue | Keywords |
---|---|---|
2008 | COLING | baseline parser,penn chinese treebank,case structure,neighboring modifier,chinese dependency parsing,semantic role,large raw corpus,large scale case structure,use case,dependency parsing |
Field | DocType | Volume |
Computer science,Dependency grammar,Speech recognition,Natural language processing,Artificial intelligence,Treebank,Parsing,Predicate (grammar),Semantic role labeling | Conference | C08-1 |
Citations | PageRank | References |
18 | 0.77 | 22 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kun Yu | 1 | 38 | 7.33 |
Daisuke Kawahara | 2 | 705 | 61.89 |
Sadao Kurohashi | 3 | 1083 | 177.05 |