DocumentCode
2337586
Title
Sentence compression by structural conversion of parse tree
Author
Egawa, Seiji ; Kato, Yoshihide ; Matsubara, Shigeki
Author_Institution
Grad. Sch. of Inf. Sci., Nagoya Univ., Nagoya
fYear
2008
fDate
13-16 Nov. 2008
Firstpage
544
Lastpage
550
Abstract
Sentence compression is the task of generating a grammatical short sentence from an original sentence, retaining important information. The existing methods of only removing the constituents in the parse tree of an original sentence cannot emulate human compression that changes structures of the parse tree. This paper proposes a method to remove recursive structures, one example of such structural conversions, and generate a grammatical short sentence. In order to remove a recursive structure, our method detects the constituents forming the structure and removes them as a unit. Compression experiments have shown that our method generates more grammatical compressed sentences than the previous method.
Keywords
data compression; grammars; natural language processing; probability; trees (mathematics); grammatical short sentence; parse tree; probability; recursive structure removal; sentence compression; structural conversion; Compression algorithms; Entropy; Humans; Information science; Information technology;
fLanguage
English
Publisher
ieee
Conference_Titel
Digital Information Management, 2008. ICDIM 2008. Third International Conference on
Conference_Location
London
Print_ISBN
978-1-4244-2916-5
Electronic_ISBN
978-1-4244-2917-2
Type
conf
DOI
10.1109/ICDIM.2008.4746757
Filename
4746757
Link To Document