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
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;
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
DOI :
10.1109/ICDIM.2008.4746757