國立虎尾科技大學 |

Semantic Operations for Transfer-Based Machine Translation.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Semantic Operations for Transfer-Based Machine Translation./
Author:	Goodman, Michael Wayne.
Description:	1 online resource (278 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 79-12(E), Section: A.
Contained By:	Dissertation Abstracts International79-12A(E).
Subject:	Linguistics. -
Online resource:	click for full text (PQDT)
ISBN:	9780438173491

Semantic Operations for Transfer-Based Machine Translation.
Goodman, Michael Wayne.

Semantic Operations for Transfer-Based Machine Translation. - 1 online resource (278 pages)

Source: Dissertation Abstracts International, Volume: 79-12(E), Section: A.

Thesis (Ph.D.)--University of Washington, 2018.

Includes bibliographical references

This dissertation describes a new approach to the automatic extraction of semantic mappings (transfer rules) for rule-based machine translation. This approach continues previous work in combining HPSG rule-based grammars, whose precise bidirectional implementation facilitates deep semantic analysis of sentences and the enumeration of grammatical realizations of semantic representations, and data-driven techniques of machine translation, whose automatic extraction of knowledge and statistical inference allow models to be quickly built from bitexts and to rank extracted patterns by their frequency. I define two new methods for bilingually aligning semantic fragments (or semantic subgraphs) and a heuristic strategy for aligning nodes between source and target subgraphs, which together allow me to design transfer systems that meet, and at times exceed, the translation coverage and quality of the prior state of the art with a significantly reduced dependence on idiosyncratic language-pair definitions (i.e., improved language independence). These improvements are made possible by a number of semantic operations, either designed or implemented by me and defined within this dissertation, that fully model the semantic representations and allow for inspection and transformation as graph operations. I apply my methods to the task of translating Japanese sentences into English---a typologically distant language pair.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780438173491Subjects--Topical Terms:

557829
Linguistics.
Index Terms--Genre/Form:

554714
Electronic books.

Semantic Operations for Transfer-Based Machine Translation.
LDR:02687ntm a2200349Ki 4500 001 916661
005 20180927111921.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438173491
035 $a (MiAaPQ)AAI10786253
035 $a (MiAaPQ)washington:18405
035 $a AAI10786253
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Goodman, Michael Wayne. $3 1190463
245 1 0 $a Semantic Operations for Transfer-Based Machine Translation.
264 0 $c 2018
300 $a 1 online resource (278 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-12(E), Section: A.
500 $a Advisers: Emily M. Bender; Francis C. Bond.
502 $a Thesis (Ph.D.)--University of Washington, 2018.
504 $a Includes bibliographical references
520 $a This dissertation describes a new approach to the automatic extraction of semantic mappings (transfer rules) for rule-based machine translation. This approach continues previous work in combining HPSG rule-based grammars, whose precise bidirectional implementation facilitates deep semantic analysis of sentences and the enumeration of grammatical realizations of semantic representations, and data-driven techniques of machine translation, whose automatic extraction of knowledge and statistical inference allow models to be quickly built from bitexts and to rank extracted patterns by their frequency. I define two new methods for bilingually aligning semantic fragments (or semantic subgraphs) and a heuristic strategy for aligning nodes between source and target subgraphs, which together allow me to design transfer systems that meet, and at times exceed, the translation coverage and quality of the prior state of the art with a significantly reduced dependence on idiosyncratic language-pair definitions (i.e., improved language independence). These improvements are made possible by a number of semantic operations, either designed or implemented by me and defined within this dissertation, that fully model the semantic representations and allow for inspection and transformation as graph operations. I apply my methods to the task of translating Japanese sentences into English---a typologically distant language pair.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Linguistics. $3 557829
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0290
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Washington. $b Linguistics. $3 1184011
773 0 $t Dissertation Abstracts International $g 79-12A(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10786253 $z click for full text (PQDT)