東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Syntactic form and discourse functio...

Creswell, Cassandre Yvonne.

FindBook

Google Book

Amazon

博客來

Syntactic form and discourse function in natural language generation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Syntactic form and discourse function in natural language generation./
作者:	Creswell, Cassandre Yvonne.
面頁冊數:	230 p.
附註:	Source: Dissertation Abstracts International, Volume: 64-04, Section: A, page: 1234.
Contained By:	Dissertation Abstracts International64-04A.
標題:	Language, Linguistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3087389

Syntactic form and discourse function in natural language generation.
Creswell, Cassandre Yvonne.

Syntactic form and discourse function in natural language generation. - 230 p.

Source: Dissertation Abstracts International, Volume: 64-04, Section: A, page: 1234.

Thesis (Ph.D.)--University of Pennsylvania, 2003.

Previous research has shown that certain discourse conditions are necessary for the felicitous use of four non-canonical syntactic constructions in English, topicalizations, left-dislocations, wh-clefts, and it-clefts. However, the distribution of these forms does not correlate one-to-one with the presence of these necessary conditions. Speakers must choose to use these constructions for other reasons. Additionally, a natural language generation algorithm that selects these statistically-rare forms based only on these conditions will overgenerate. If it selects clausal word order based only on frequency, however, these forms will never be selected or will be used in meaningless ways. The purpose of this dissertation is to devise a more complete model of when human speakers generate these constructions in order to further understanding of syntactic form selection and to better characterize these forms' conditions of use for purposes of NLG. The model of syntactic choice presented explicitly ties the goals of the communicative agent to the linguistic forms selected to achieve those goals. Three types of communicative goals that speakers achieve through the use of non-canonical syntax are argued for (1) attention marking, (2) discourse relation, and (3) information-structure focus disambiguation. The evidence supporting the model is based on naturally-occurring tokens from a corpus of spontaneous oral discourse. This same corpus, annotated with low-level properties of the discourse context surrounding utterances with non-canonical word order, is then used to train a statistical model that can approximate some aspects of the theoretical model. The statistical model supports the claim that communicative goals of signaling discourse relations do correlate significantly with the use of particular non-canonical forms. The statistical model is also used as a probabilistic classifier, which could be utilized as a stochastic method for selecting syntactic form based on discourse context as part of a natural language generation system. The probabilistic classifier shows improvement over a naive classifier when applied to training data. The probabilistic classifier is a first attempt to utilize more than just frequency counts as a basis for syntactic form selection and instead incorporate aspects of the semantic content of surrounding discourse context as a basis for using a particular form.Subjects--Topical Terms:

1018079
Language, Linguistics.

Syntactic form and discourse function in natural language generation.
LDR:03345nmm 2200277 4500 001 1858768
005 20041020094116.5
008 130614s2003 eng d
035 $a (UnM)AAI3087389
035 $a AAI3087389
040 $a UnM $c UnM
100 1 $a Creswell, Cassandre Yvonne. $3 1946450
245 1 0 $a Syntactic form and discourse function in natural language generation.
300 $a 230 p.
500 $a Source: Dissertation Abstracts International, Volume: 64-04, Section: A, page: 1234.
500 $a Supervisors: Aravind Joshi; Ellen Prince.
502 $a Thesis (Ph.D.)--University of Pennsylvania, 2003.
520 $a Previous research has shown that certain discourse conditions are necessary for the felicitous use of four non-canonical syntactic constructions in English, topicalizations, left-dislocations, wh-clefts, and it-clefts. However, the distribution of these forms does not correlate one-to-one with the presence of these necessary conditions. Speakers must choose to use these constructions for other reasons. Additionally, a natural language generation algorithm that selects these statistically-rare forms based only on these conditions will overgenerate. If it selects clausal word order based only on frequency, however, these forms will never be selected or will be used in meaningless ways. The purpose of this dissertation is to devise a more complete model of when human speakers generate these constructions in order to further understanding of syntactic form selection and to better characterize these forms' conditions of use for purposes of NLG. The model of syntactic choice presented explicitly ties the goals of the communicative agent to the linguistic forms selected to achieve those goals. Three types of communicative goals that speakers achieve through the use of non-canonical syntax are argued for (1) attention marking, (2) discourse relation, and (3) information-structure focus disambiguation. The evidence supporting the model is based on naturally-occurring tokens from a corpus of spontaneous oral discourse. This same corpus, annotated with low-level properties of the discourse context surrounding utterances with non-canonical word order, is then used to train a statistical model that can approximate some aspects of the theoretical model. The statistical model supports the claim that communicative goals of signaling discourse relations do correlate significantly with the use of particular non-canonical forms. The statistical model is also used as a probabilistic classifier, which could be utilized as a stochastic method for selecting syntactic form based on discourse context as part of a natural language generation system. The probabilistic classifier shows improvement over a naive classifier when applied to training data. The probabilistic classifier is a first attempt to utilize more than just frequency counts as a basis for syntactic form selection and instead incorporate aspects of the semantic content of surrounding discourse context as a basis for using a particular form.
590 $a School code: 0175.
650 4 $a Language, Linguistics. $3 1018079
650 4 $a Language, Modern. $3 1018098
690 $a 0290
690 $a 0291
710 2 0 $a University of Pennsylvania. $3 1017401
773 0 $t Dissertation Abstracts International $g 64-04A.
790 1 0 $a Joshi, Aravind, $e advisor
790 1 0 $a Prince, Ellen, $e advisor
790 $a 0175
791 $a Ph.D.
792 $a 2003
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3087389