東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Head-driven probabilistic parsing fo...

Collins, Christopher.

Linked to FindBook

Google Book

Amazon

博客來

Head-driven probabilistic parsing for word lattices.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Head-driven probabilistic parsing for word lattices./
Author:	Collins, Christopher.
Description:	111 p.
Notes:	Source: Masters Abstracts International, Volume: 42-06, page: 2226.
Contained By:	Masters Abstracts International42-06.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MQ91446
ISBN:	0612914461

Head-driven probabilistic parsing for word lattices.
Collins, Christopher.

Head-driven probabilistic parsing for word lattices. - 111 p.

Source: Masters Abstracts International, Volume: 42-06, page: 2226.

Thesis (M.Sc.)--University of Toronto (Canada), 2004.

This thesis presents the first application of the state-of-the-art head-driven statistical parsing model of Collins (1999) as a simultaneous language model and parser for large-vocabulary speech recognition. The model is adapted to an online left to right chart-parser for word lattices, integrating acoustic, N-gram, and parser probabilities. The parser uses structural and lexical dependencies not considered by N-gram models, conditioning recognition on more linguistically-grounded relationships. By preferring paths through the word lattice for which a probable parse exists, word error rate can be reduced and important syntactic and semantic relationships can be determined in a single step process. New forms of heuristic search and pruning are employed to improve efficiency. Experiments on the Wall Street Journal treebank and lattice corpora show word error rates competitive with the standard N-gram language model while extracting additional structural information useful for speech understanding.

ISBN: 0612914461Subjects--Topical Terms:

626642
Computer Science.

Head-driven probabilistic parsing for word lattices.
LDR:01828nmm 2200265 4500 001 1847051
005 20051103093615.5
008 130614s2004 eng d
020 $a 0612914461
035 $a (UnM)AAIMQ91446
035 $a AAIMQ91446
040 $a UnM $c UnM
100 1 $a Collins, Christopher. $3 788988
245 1 0 $a Head-driven probabilistic parsing for word lattices.
300 $a 111 p.
500 $a Source: Masters Abstracts International, Volume: 42-06, page: 2226.
500 $a Adviser: Gerald Penn.
502 $a Thesis (M.Sc.)--University of Toronto (Canada), 2004.
520 $a This thesis presents the first application of the state-of-the-art head-driven statistical parsing model of Collins (1999) as a simultaneous language model and parser for large-vocabulary speech recognition. The model is adapted to an online left to right chart-parser for word lattices, integrating acoustic, N-gram, and parser probabilities. The parser uses structural and lexical dependencies not considered by N-gram models, conditioning recognition on more linguistically-grounded relationships. By preferring paths through the word lattice for which a probable parse exists, word error rate can be reduced and important syntactic and semantic relationships can be determined in a single step process. New forms of heuristic search and pruning are employed to improve efficiency. Experiments on the Wall Street Journal treebank and lattice corpora show word error rates competitive with the standard N-gram language model while extracting additional structural information useful for speech understanding.
590 $a School code: 0779.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 0 $a University of Toronto (Canada). $3 1017674
773 0 $t Masters Abstracts International $g 42-06.
790 1 0 $a Penn, Gerald, $e advisor
790 $a 0779
791 $a M.Sc.
792 $a 2004
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MQ91446