Kenneth D. Forbus, Kate Lockwood, E. Tomai, Morteza Dehghani, Jakub Czyz
We describe how we are using natural language techniques to develop systems that can automatically encode a range of input materials for cognitive simulations. We start by summarizing this type of problem, and the components we are using. We then describe three projects that are using this common infrastructure: learning from multimodal materials, modeling decision making in moral dilemmas, and modeling conceptual change in development.
{"title":"Machine Reading as a Cognitive Science Research Instrument","authors":"Kenneth D. Forbus, Kate Lockwood, E. Tomai, Morteza Dehghani, Jakub Czyz","doi":"10.21236/ADA470412","DOIUrl":"https://doi.org/10.21236/ADA470412","url":null,"abstract":"We describe how we are using natural language techniques to develop systems that can automatically encode a range of input materials for cognitive simulations. We start by summarizing this type of problem, and the components we are using. We then describe three projects that are using this common infrastructure: learning from multimodal materials, modeling decision making in moral dilemmas, and modeling conceptual change in development.","PeriodicalId":145241,"journal":{"name":"AAAI Spring Symposium: Machine Reading","volume":"2003 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128709593","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}
Kenneth D. Forbus, C. Riesbeck, L. Birnbaum, K. Livingston, Abhishek B. Sharma, Leo C. Ureel
Systems that could learn by reading would radically change the economics of building large knowledge bases. This paper describes Learning Reader, a prototype system that extends its knowledge base by reading. Learning Reader consists of three components. The Reader, which converts text into formally represented cases, uses a Direct Memory Access Parser operating over a large knowledge base, derived from ResearchCyc. The Q/A system, which provides a means of quizzing the system on what it has learned, uses focused sets of axioms automatically extracted from the knowledge base for tractability. The Ruminator, which attempts to improve the system's understanding of what it has read by off-line processing, generates questions for itself by several means, including analogies with prior material and automatically constructed generalizations from examples in the KB and its prior reading. We discuss the architecture of the system, how each component works, and some experimental results.
{"title":"A Prototype System that Learns by Reading Simplified Texts","authors":"Kenneth D. Forbus, C. Riesbeck, L. Birnbaum, K. Livingston, Abhishek B. Sharma, Leo C. Ureel","doi":"10.21236/ada470413","DOIUrl":"https://doi.org/10.21236/ada470413","url":null,"abstract":"Systems that could learn by reading would radically change the economics of building large knowledge bases. This paper describes Learning Reader, a prototype system that extends its knowledge base by reading. Learning Reader consists of three components. The Reader, which converts text into formally represented cases, uses a Direct Memory Access Parser operating over a large knowledge base, derived from ResearchCyc. The Q/A system, which provides a means of quizzing the system on what it has learned, uses focused sets of axioms automatically extracted from the knowledge base for tractability. The Ruminator, which attempts to improve the system's understanding of what it has read by off-line processing, generates questions for itself by several means, including analogies with prior material and automatically constructed generalizations from examples in the KB and its prior reading. We discuss the architecture of the system, how each component works, and some experimental results.","PeriodicalId":145241,"journal":{"name":"AAAI Spring Symposium: Machine Reading","volume":"25 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125954774","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：