Docket Number:05A-880527
Inventor: Chun-Nan Hsu, Chian-Chi Chang
IP Status:TW I145175
Abstract:
An information extractor for extracting subsets of text sequences having certain attributes from a semi-structured text sequence. The information extractor resembles a finite state transducer that includes a number of states and transition paths between the states. Each state is defined to be associated with the extraction of subsets of tokens having a certain attribute. Each transition path represents a possible transition from one subset of tokens having a certain attribute to another subset of tokens having another attribute. Contextual rules are used to determine when a transition occurs and which transition path to take. By using contextual rules that consider the token patterns before and after a token, the information extractor can process documents with irregular layout structures and attributes having a greater variety of permutations.
Contact Person:
對本技術有興趣,請於本處網頁廠商選項下(廠商需求與諮詢)網頁填寫資料,承辦人將跟您聯絡。
If you are interested in this technology, please fill in the information on the webpage under the manufacturer option (Apply for Technology Licensing, Material Transfer, or Sponsored Research) on the website of this office, and the undertaker will contact you
