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

Automatic inference: A probabilistic...

Wu, Dekai.

FindBook

Google Book

Amazon

博客來

Automatic inference: A probabilistic basis for natural language interpretation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Automatic inference: A probabilistic basis for natural language interpretation./
作者:	Wu, Dekai.
面頁冊數:	311 p.
附註:	Source: Dissertation Abstracts International, Volume: 53-10, Section: B, page: 5309.
Contained By:	Dissertation Abstracts International53-10B.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9305122

Automatic inference: A probabilistic basis for natural language interpretation.
Wu, Dekai.

Automatic inference: A probabilistic basis for natural language interpretation. - 311 p.

Source: Dissertation Abstracts International, Volume: 53-10, Section: B, page: 5309.

Thesis (Ph.D.)--University of California, Berkeley, 1992.

This work proposes a probabilistic basis for natural language understanding models. It has become apparent that syntax and semantics need to be highly integrated, especially to understand constructs like nominal compounds, but inadequate modelling tools have hindered efforts to replace the traditional parser-interpreter pipeline architecture. Qualitatively, associative frameworks like spreading activation and marker passing produce the desired interactions, but their reliance on ad hoc numeric weights make scaling them up to interestingly large domains difficult. On the other hand, statistical approaches ground numeric measures over large domains, but have thus far failed to incorporate the structural generalizations found in traditional models. A major reason for this is the inability of most statistical language models to represent compositional constraints; this is related to the variable binding problem in neural networks.Subjects--Topical Terms:

626642
Computer Science.

Automatic inference: A probabilistic basis for natural language interpretation.
LDR:03254nmm 2200289 4500 001 1852234
005 20051229080826.5
008 130614s1992 eng d
035 $a (UnM)AAI9305122
035 $a AAI9305122
040 $a UnM $c UnM
100 1 $a Wu, Dekai. $3 1940100
245 1 0 $a Automatic inference: A probabilistic basis for natural language interpretation.
300 $a 311 p.
500 $a Source: Dissertation Abstracts International, Volume: 53-10, Section: B, page: 5309.
502 $a Thesis (Ph.D.)--University of California, Berkeley, 1992.
520 $a This work proposes a probabilistic basis for natural language understanding models. It has become apparent that syntax and semantics need to be highly integrated, especially to understand constructs like nominal compounds, but inadequate modelling tools have hindered efforts to replace the traditional parser-interpreter pipeline architecture. Qualitatively, associative frameworks like spreading activation and marker passing produce the desired interactions, but their reliance on ad hoc numeric weights make scaling them up to interestingly large domains difficult. On the other hand, statistical approaches ground numeric measures over large domains, but have thus far failed to incorporate the structural generalizations found in traditional models. A major reason for this is the inability of most statistical language models to represent compositional constraints; this is related to the variable binding problem in neural networks.
520 $a The proposed model attacks these issues from three directions. First, it distinguishes two fundamentally different mental processing modes: automatic and controlled inference. Automatic inference is pre-attentive, subconscious, reflexive, fairly instantaneous, associative, and highly heuristic; this delimits the domain of parallel interactive processing. Automatic inference is motivated by both resource bounds and empirical criteria, and is responsible for much if not most of parsing and semantic interpretation.
520 $a Second, the nature of mental representations is defined more precisely. The proposed cognitive ontology includes mental images, lexical semantics, conceptual, and lexicosyntactic modules. Automatic inference extends over all modules. The modular ontology approach accounts for a range of subtle meaning distinctions, is consistent with psycholinguistic and neural evidence, and helps reduce the complexity of the concept space.
520 $a Third, probability theory provides an elegant basis for evidential interpretation, to model automatic inference in language understanding. A uniform representation for all the modules is proposed, compatible with both feature-structures and semantic networks. Probabilistic, associative extensions are then made to those frameworks. Theoretical and approximate maximum entropy methods for evaluating probabilities are proposed, as well as the basis for a normative distribution for learning and generalization.
590 $a School code: 0028.
650 4 $a Computer Science. $3 626642
650 4 $a Language, Linguistics. $3 1018079
650 4 $a Psychology, General. $3 1018034
690 $a 0984
690 $a 0290
690 $a 0621
710 2 0 $a University of California, Berkeley. $3 687832
773 0 $t Dissertation Abstracts International $g 53-10B.
790 $a 0028
791 $a Ph.D.
792 $a 1992
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9305122