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

Computational approaches to linguist...

Wang, Jun.

Linked to FindBook

Google Book

Amazon

博客來

Computational approaches to linguistic consensus.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Computational approaches to linguistic consensus./
Author:	Wang, Jun.
Description:	106 p.
Notes:	Source: Dissertation Abstracts International, Volume: 68-02, Section: A, page: 0386.
Contained By:	Dissertation Abstracts International68-02A.
Subject:	Language, Linguistics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3250342

Computational approaches to linguistic consensus.
Wang, Jun.

Computational approaches to linguistic consensus. - 106 p.

Source: Dissertation Abstracts International, Volume: 68-02, Section: A, page: 0386.

Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2006.

The main question we ask is how a common language might come about in complex adaptive language systems comprising many agents. Our primary objective is to analyze and design complex language models so that a group of agents can converge on a common language from their initially different languages by using reinforcement learning, a minimal information approach. Towards this end, we present a game-based self-organizing language framework, and study three important cases of reaching linguistic consensus: word consensus, coherent communication, and grammar consensus.Subjects--Topical Terms:

1018079
Language, Linguistics.

Computational approaches to linguistic consensus.
LDR:03125nmm 2200325 4500 001 1834985
005 20071129070349.5
008 130610s2006 eng d
035 $a (UMI)AAI3250342
035 $a AAI3250342
040 $a UMI $c UMI
100 1 $a Wang, Jun. $3 892864
245 1 0 $a Computational approaches to linguistic consensus.
300 $a 106 p.
500 $a Source: Dissertation Abstracts International, Volume: 68-02, Section: A, page: 0386.
500 $a Adviser: Les Gasser.
502 $a Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2006.
520 $a The main question we ask is how a common language might come about in complex adaptive language systems comprising many agents. Our primary objective is to analyze and design complex language models so that a group of agents can converge on a common language from their initially different languages by using reinforcement learning, a minimal information approach. Towards this end, we present a game-based self-organizing language framework, and study three important cases of reaching linguistic consensus: word consensus, coherent communication, and grammar consensus.
520 $a The study of word consensus concerns how agents can converge to a common word to reliably express a single shared meaning, out of a number of different words. We have proposed a win-stay lose-shift learning model, and have shown by computer simulation and mathematical analysis the conditions under which the agents in the model can converge to a common word.
520 $a The study of coherent communication concerns how agents can converge on a communication system in which the word used by a sender to represent some meaning can be interpreted correctly by a receiver to extract the same meaning. We have proposed a minimum reinforcement learning model comprising two agents (a sender and a receiver), and have shown by computer simulation and mathematical analysis the conditions under which agents in the model can converge to a coherent communication system.
520 $a The study of grammar consensus concerns how agents can converge to a common grammar. In the converged state, the sentences generated by one agent using his grammar can be recognized by another agent using her grammar. We have proposed a mutual perceptron learning model in which grammars are modeled as Boolean functions that can be used to classify or recognize Boolean instances (sentences), and have shown by mathematical analysis the conditions under which agents in this model can converge to a common grammar (i.e., a common Boolean function).
520 $a This work has important implications for many kinds of distributed semantic systems, such as shared web ontologies, agent communication protocols, collaborative tagging, database schema integration, and biological networks.
590 $a School code: 0090.
650 4 $a Language, Linguistics. $3 1018079
650 4 $a Information Science. $3 1017528
650 4 $a Computer Science. $3 626642
690 $a 0290
690 $a 0723
690 $a 0984
710 2 0 $a University of Illinois at Urbana-Champaign. $3 626646
773 0 $t Dissertation Abstracts International $g 68-02A.
790 1 0 $a Gasser, Les, $e advisor
790 $a 0090
791 $a Ph.D.
792 $a 2006
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3250342