基于CBR的双语语境知识表征系统研究  

Simulating Bilingual Contextual Knowledge of Chinese Learners of English

作　　者：牛书杰[1] 李红[1] 

机构地区：[1]重庆大学语言认知及语言应用研究基地,重庆400044

出　　处：《重庆大学学报（社会科学版）》2009年第6期144-148,共5页Journal of Chongqing University(Social Science Edition)

基　　金：2007年重庆大学人文社科青年教师科研基金项目"基于计算机模拟的第二语言习得研究"(CDSK2006-20)

摘　　要：文章简要回顾了基于案例①的推理(case-based reasoning,简称CBR)机制和第二语言习得理论中"补缺假设"理论的语境观,分析了CBR在双语语境知识表征中应用的可行性,并在此基础上提出了双语语境知识表征CBR系统的计算模型、算法和该系统的一般实现过程,是机器学习和人工智能理论在第二语言习得理论研究中应用的初步探讨,旨在给第二语言习得研究提供新的研究方法和视角。This paper, by constructing a CBR-based computational model, attempts to evaluate the validity of the Compensation Hypothesis, an SLA theory proposed by Professor Wang Churning for the purpose of elucidating the cognitive mechanisms of Chinese learners of English. Instead of simulating the processes of phonological, lexical, semantic or syntactical acquisition, as is often done in first language acquisition research, the paper, based on the Compensation Hypothesis, examines the feasibility of modeling the cognitive mechanisms of bilingual contextual knowledge acquisition. This model holds that bilingual contextual knowledge can be best represented by the use of case-based reasoning, not rule-based reasoning. The architecture of the CBR-based model is detailed, related algorithm for the system proposed and a case-based corpus depicted. The computational model can account for some of the issues in SLA research, such as Chinglish, fossilization, etc. This methodology can also serve as an alternative research paradigm for SLA studies.

关 键 词：案例(CBR) 推理 补缺假设 认知模拟 语境 

分 类 号：H319[语言文字—英语]