DocumentCode :
1411278
Title :
A parallel system for text inference using marker propagations
Author :
Harabagiu, Sanda M. ; Moldovan, Dan I.
Author_Institution :
Dept. of Comput. Sci. & Eng., Southern Methodist Univ., Dallas, TX, USA
Volume :
9
Issue :
8
fYear :
1998
fDate :
8/1/1998 12:00:00 AM
Firstpage :
729
Lastpage :
747
Abstract :
This paper presents a possible solution for the text inference problem-extracting information unstated in a text, but implied. Text inference is central to natural language applications such as information extraction and dissemination, text understanding, summarization, and translation. Our solution takes advantage of a semantic English dictionary available in electronic form that provides the basis for the development of a large linguistic knowledge base. The inference algorithm consists of a set of highly parallel search methods that, when applied to the knowledge base, find contexts in which sentences are interpreted. These contexts reveal information relevant to the text. Implementation, results, and parallelism analysis are discussed
Keywords :
inference mechanisms; knowledge acquisition; natural languages; parallel algorithms; search problems; dissemination; information extraction; knowledge base; linguistic knowledge base; natural language; semantic English dictionary; text inference; text understanding; Computer Society; Computer science; Data mining; Humans; Inference algorithms; Information retrieval; Natural language processing; Natural languages; Parallel processing; Text recognition;
fLanguage :
English
Journal_Title :
Parallel and Distributed Systems, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9219
Type :
jour
DOI :
10.1109/71.706046
Filename :
706046
Link To Document :
بازگشت