Database Management White Papers
Bidirectional Incremental Parsing for Automatic Pathway Identification with Combinatory Categorial Grammar
Overview This paper describes an implemented system that utilizes combinatory categorial grammar known to be competent in modeling natural language, with a controlled mechanism for the parser to operate bidirectionally and incrementally. It discusses the performance of the system on a large set of abstracts in Medline with quite encouraging results. The need for automating the process of extracting and analyzing natural language assertions about protein-protein interactions in biomedical publications is well recognized, given the ever increasing volume and importance of the archived collection of natural language documents in databases such as Medline. The field has two complementary aspects from the natural language processing perspective. On the one hand, the terminology is not only immense already but also rapidly growing, challenging the use of a pre-defined lexicon alone. On the other, the type of interactions is relatively fixed, where one can find corresponding natural language predicates in a pre-determined manner.
| Publisher | Stanford Knowledgebase | File Format | PDF, requires Acrobat Rdr 5 |
|---|---|---|---|
| Date Published | September 2001 | Downloads | 93 |
| Format | White Papers | ||
| Topics | |||
-
Did you find this white paper useful? 2 out of 4 users found this white paper useful
White Paper RSS
Download
Register
