[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91最新文献

筛选
英文 中文
AUTOTEC: an English to Chinese machine translation system AUTOTEC:一个中英文机器翻译系统
K. Chen
{"title":"AUTOTEC: an English to Chinese machine translation system","authors":"K. Chen","doi":"10.1109/TAI.1991.167035","DOIUrl":"https://doi.org/10.1109/TAI.1991.167035","url":null,"abstract":"An English to Chinese MT (machine translation) system, AUTOTEC, which uses a multilevel reconstruction approach, is presented. The translation in the system is performed in a sequential, phrasal, and lexical order. Through the hierarchical processing, the large linguistic differences between English and Chinese can be well bridged.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114152062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Selective relaxation for constraint satisfaction problems 约束满足问题的选择性松弛
Eugene C. Freuder, R. Wallace
{"title":"Selective relaxation for constraint satisfaction problems","authors":"Eugene C. Freuder, R. Wallace","doi":"10.1109/TAI.1991.167112","DOIUrl":"https://doi.org/10.1109/TAI.1991.167112","url":null,"abstract":"A basic problem is to optimize the tradeoff between effort required to establish a local consistency and that required for search. An approach is presented to this problem which is termed selective relaxation. The idea is to perform consistency checking at places where it is likely to be effective, basing this judgment on local criteria. To this end, the authors introduce two forms of bounded relaxation, one in which consistency testing propagates for a limited distance from a point of change, and one in which it stops when the amount of change, or response, falls below threshold. Experiments show that these procedures can outperform well-known preprocessing or hybrid algorithms on many problems.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121733583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 19
Historical Rete networks for debugging rule-based systems 用于调试基于规则的系统的历史远程网络
Sharon M. Tuttle, C. Eick
{"title":"Historical Rete networks for debugging rule-based systems","authors":"Sharon M. Tuttle, C. Eick","doi":"10.1109/TAI.1991.167127","DOIUrl":"https://doi.org/10.1109/TAI.1991.167127","url":null,"abstract":"To debug a forward-chaining rule-based program, certain, historical, information is needed. System builders should be able to request such information directly, instead of having to rerun the program one step at a time or search a trace of run details. As a first step in designing an explanation system for answering such questions, a proposal is discussed for storing a forward-chaining program run's 'historical' details in its Rete inference network, used to match rule conditions to working memory, without seriously affecting the network's run-time performance. This proposed modified Rete network is called a historical Rete network. Various algorithms for maintaining this network are discussed, along with how it can be used to analyze what happened during a program run.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129813397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Incremental binding-space match: the linearized matchbox algorithm 增量绑定空间匹配:线性化火柴盒算法
M. Perlin
{"title":"Incremental binding-space match: the linearized matchbox algorithm","authors":"M. Perlin","doi":"10.1109/TAI.1991.167028","DOIUrl":"https://doi.org/10.1109/TAI.1991.167028","url":null,"abstract":"A new binding-space algorithm conjunctive match is introduced. Known as the linearized match box, it improves on the parallel match box algorithm by reducing broadcast cost, better adapting it to serial computers. Cost estimates are presented that help determine the applicability of linearized match box for particular rule problems. Linearized match box has been implemented, and its utility in overcoming PRODIGY's control knowledge bottleneck is discussed.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"225 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116315381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
MANTRA: a shell for hybrid knowledge representation MANTRA:混合知识表示的外壳
J. Calmet, Indra A. Tjandra, G. Bittencourt
{"title":"MANTRA: a shell for hybrid knowledge representation","authors":"J. Calmet, Indra A. Tjandra, G. Bittencourt","doi":"10.1109/TAI.1991.167091","DOIUrl":"https://doi.org/10.1109/TAI.1991.167091","url":null,"abstract":"A shell is presented for hybrid knowledge representation. This system supports four different knowledge representation formalisms: first-order logic, terminological language, semantic networks, and production systems. The system automatically supports hybrid inferences taking into account the knowledge represented in different formalisms. All the algorithms involved in the inferences, supported by the system, are decidable, and have the property of being sound and complete according to a four-valued semantics. Besides these facilities, the shell allows the user to represent procedural knowledge of a domain using the primitives embedded at the heuristic level. The system has been implemented in Common Lisp, and makes use of an object-oriented extension for this language.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130384341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 17
Boundary detection based on neural networks model 基于神经网络模型的边界检测
D. C. D. Hung, Ke Chen
{"title":"Boundary detection based on neural networks model","authors":"D. C. D. Hung, Ke Chen","doi":"10.1109/TAI.1991.167102","DOIUrl":"https://doi.org/10.1109/TAI.1991.167102","url":null,"abstract":"A new model of feedforward neural networks is proposed for solving the problem of robust boundary detection. Structurally, it is based on a circular mask which is characterized as a symmetrical neural network. By analyzing the weighted intermediate pattern, a dominant pattern is found to appear repeatedly for similar boundary orientation. Hence, a piecewise linearized edge could be detected by this approximation. Experimental results show that this new architecture can be applied to experience scaling effect by changing the mask size.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"11 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132472059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Toward a theory approach to visual knowledge 走向视觉知识的理论途径
Jianxiang Wang, Yongchun Liu, Shenquan Liu
{"title":"Toward a theory approach to visual knowledge","authors":"Jianxiang Wang, Yongchun Liu, Shenquan Liu","doi":"10.1109/TAI.1991.167048","DOIUrl":"https://doi.org/10.1109/TAI.1991.167048","url":null,"abstract":"A discussion is presented of visual knowledge related to computer graphics and pattern recognition. Based on the visual knowledge model, some main principles of visual knowledge, including the preliminary definition, the classification of visual knowledge, a set of operating rules, and a method of learning concepts, are proposed.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131837610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
The use of version space controlled genetic algorithms to solve the Boole problem 利用版本空间控制遗传算法解决布尔问题
R. Reynolds, Jonathan I. Maletic
{"title":"The use of version space controlled genetic algorithms to solve the Boole problem","authors":"R. Reynolds, Jonathan I. Maletic","doi":"10.1109/TAI.1991.167071","DOIUrl":"https://doi.org/10.1109/TAI.1991.167071","url":null,"abstract":"It is demonstrated that the VGA (version space guided genetic algorithm) is a particular instantiation of a more general class of systems, termed autonomous learning elements (ALEs). The basic components of an ALEs are discussed. The Boole problem posed by S. W. Wilson (1987) is introduced, and its expression in terms of the VGA framework is discussed. The details of the VGA system are given followed by a discussion of results. In particular, the performances of the VGA on two versions of the Boole problem are described and compared with those of classifier systems and decision trees.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115996587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 13
The C++ embeddable rule system 可嵌入的c++规则系统
Daniel P. Miranker, F. H. Burke, Jeri J. Steele, J. Kolts, David R. Haug
{"title":"The C++ embeddable rule system","authors":"Daniel P. Miranker, F. H. Burke, Jeri J. Steele, J. Kolts, David R. Haug","doi":"10.1109/TAI.1991.167119","DOIUrl":"https://doi.org/10.1109/TAI.1991.167119","url":null,"abstract":"Most rule execution environments, having been derived from LISP, inference on internally defined data types and come packaged with stand-alone development environments. Data derived from outside these systems must be reformatted before they can be evaluated. This mismatch leads to a duplicate representation of data, which, in turn, introduces both performance and semantic problems. A description is given of a C++ embeddable rule system (CERS) which avoid this mismatch. CERS is a compiled, forward-chaining rule system that inferences directly on arbitrary C++ objects. CERS can be viewed as an extension of C++, where object methods can be defined either procedurally or declaratively.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126509192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 18
RETE and chart parsing from bottom-up call-graph caching 从自下而上的调用图缓存进行RETE和图表解析
M. Perlin
{"title":"RETE and chart parsing from bottom-up call-graph caching","authors":"M. Perlin","doi":"10.1109/TAI.1991.167027","DOIUrl":"https://doi.org/10.1109/TAI.1991.167027","url":null,"abstract":"A new mechanism is presented for graph instantiation. It is used to investigate various bottom-up data-driven AI algorithms. The author views instances as fairly autonomous objects that inherit graph information (e.g. links or relations) from their classes. Instances themselves can be instantiated. For example, a parse tree symbol is an instance of a grammar class-graph symbol, which itself is a symbol of instance. The model focuses on underlying computational processes, and makes little use of program text. Instead of transforming programs, CGC (call graph caching) is used to instantiate processes. Experimental results show that RETE matching, efficient context-free parsing, and truth maintenance are different manifestations of the same underlying computational process.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120950361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信