Filters








785 Hits in 4.3 sec

Knowledge Engineering [chapter]

2014 Encyclopedia of Social Network Analysis and Mining  
interaction with the user, as well as the solving of domain problems.  ...  The CYC project to represent a portable set of general knowledge that can be used as a basis for any novel system is described.  ...  The natural language modes use conventional natural language processing techniques, the graphics mode uses explicit knowledge about the design of graphic presentations drawn from design theory and designer's  ... 
doi:10.1007/978-1-4614-6170-8_100788 fatcat:iiauuwgtdrhbpfgflleheaf6pu

Introduction to the Special Issue on Question Answering

David Gunning, Vinay K. Chaudhri, Chris Welty
2010 The AI Magazine  
This special issue issue of AI Magazine presents six articles on some of the most interesting question answering systems in development today.  ...  Included are articles on Project, the Semantic Research, Watson, True Knowledge, and TextRunner (University of Washington's clever use of statistical NL techniques to answer questions across the open web  ...  plus Horn Rules Mixed Triples Triples of text Knowledge Acquisition Manual Manual Mixed Mixed Automatic Question Form Interactive Natural Language Controlled Natural Language  ... 
doi:10.1609/aimag.v31i3.2300 fatcat:ytotrlhuvnbynitvsih5np3p6a

Common Sense Reasoning – From Cyc to Intelligent Assistant [chapter]

Kathy Panton, Cynthia Matuszek, Douglas Lenat, Dave Schneider, Michael Witbrock, Nick Siegel, Blake Shepard
2006 Lecture Notes in Computer Science  
The underlying philosophy of the Cyc Project is that software will never reach its full potential until it can react flexibly to a variety of challenges.  ...  and hypothesis formation), which must be integrated into the Cyc reasoning system and Knowledge Base to be fully effective.  ...  The Evolution of Cyc Beginnings of the Cyc Project Acknowledgements Research as wide-ranging and ambitious as the Cyc Project and the many components described in this paper would not be possible without  ... 
doi:10.1007/11825890_1 fatcat:eth3tvhdavgm5mbf5wllynwyfa

Contextualized Question Answering

Luka Bradesko, Lorand Dali, Blaz Fortuna, Marko Grobelnik, Dunja Mladenic, Inna Novalija, Bostjan Pajntar
2010 Journal of Computing and Information Technology  
The possibility of asking natural language questions enables a friendly interaction for the user.The contextualization is achieved by using an ontology.  ...  as Cyc, ASFA and WordNet.  ...  Here we have used a part of Cyc functionality that includes the Knowledge base, Inference Engine and The Natural Language Processing Subsystem, which we accessed through Cyc Developer Toolsets (CYC API  ... 
doi:10.2498/cit.1001912 fatcat:lpcrdakkhbcxfgwn5zefxudxse

Commonsense reasoning and commonsense knowledge in artificial intelligence

Ernest Davis, Gary Marcus
2015 Communications of the ACM  
(A closely related issue is the representation of the meaning of natural language sentences. 45 ) ˲ Plausible inference; drawing provisional or uncertain conclusions. ˲ Range of reasoning modes.  ...  best explanation.  ... 
doi:10.1145/2701413 fatcat:tc4gobnmxrdxrjv6e5toax6elq

Do Fine-tuned Commonsense Language Models Really Generalize? [article]

Mayank Kejriwal, Ke Shen
2020 arXiv   pre-print
Recently, transformer-based methods such as RoBERTa and GPT-3 have led to significant experimental advances in natural language processing tasks such as question answering and commonsense reasoning.  ...  The latter is typically evaluated through multiple benchmarks framed as multiple-choice instances of the former.  ...  Examples are provided in Figure 1 . 1. aNLI (Abductive Natural Language Inference): Abductive Natural Language Inference (aNLI) 2 (Bhagavatula et al. 2020) is a new commonsense benchmark dataset designed  ... 
arXiv:2011.09159v1 fatcat:pa4ruffdffaunakztgves7tdoq

The situated common-sense knowledge in FunGramKB

Carlos Periñán-Pascual
2012 Review of Cognitive Linguistics  
The objective of this paper is to present a script model as a carrier of the situated common-sense knowledge required to help knowledge engineers construct more "intelligent" natural language processing  ...  Discourse inferences are grounded on the shared generalized knowledge which is activated from the situational model underlying the text surface dimension.  ...  This lack of a formal language implies that it is not only more difficult to be precise, but natural language fragments may also be full of ambiguity.  ... 
doi:10.1075/rcl.10.1.06per fatcat:a4wlccax7bbj3ad5ke6axnspze

Analogy and Relational Representations in the Companion Cognitive Architecture

Kenneth D. Forbus, Thomas Hinrich
2017 The AI Magazine  
The Companion cognitive architecture is aimed at reaching human-level AI by creating software social organisms, systems that interact with people using natural modalities, working and learning over extended  ...  periods of time as collaborators rather than tools.  ...  Statements and opinions expressed may not reflect the position or policy of the United States government, and no official endorsement should be inferred. David Barbella  ... 
doi:10.1609/aimag.v38i4.2743 fatcat:ex3vwybbjvg6xcg4ktdjkg646i

True Knowledge: Open-Domain Question Answering Using Structured Knowledge and Inference

William Tunstall-Pedoe
2010 The AI Magazine  
The system combines a large and growing structured knowledge base of common sense, factual and lexical knowledge; a natural language translation system that turns user questions into internal language-independent  ...  queries and an inference system that can answer those queries using both directly represented and inferred knowledge.  ...  However, there is no natural language question-answering ability (though Powerset has applied its natural language capabilities to Freebase data).  ... 
doi:10.1609/aimag.v31i3.2298 fatcat:6amwxs7xmffehmr3p4jafnmrki

Context in problem solving: a survey

Patrick Brézillon
1999 Knowledge engineering review (Print)  
However, context is already considered in other domains, such as Natural Language Processing, although through few aspects of context.  ...  One of the conclusions of this survey is to point out the existence of different types of context along knowledge representation, the mechanisms of reasoning on the knowledge, and the interaction of the  ...  Always in the area of Natural Language Generation, Pereira and Pollack (1991) present a system, called Candide, to incrementally interpret natural-language utterances in context.  ... 
doi:10.1017/s0269888999141018 fatcat:mt2pv42kobb3xjwxjcz4piyzne

CYC: A Midterm Report

Ramanathan V. Guha, Douglas B. Lenat
1990 The AI Magazine  
The heuristic level consists of several modules for generating and comparing arguments for and against a given proposition.  ...  A user (human or application program) will usually communicate with Cyc at the epistemological level, and their utterances are translated by the tell-ask (TA) interface into heuristic-level propositions  ...  Acknowledgments We would like to thank Mary Shepherd for her patience and help since the inception of the Cyc project.  ... 
doi:10.1609/aimag.v11i3.842 dblp:journals/aim/GuhaL90 fatcat:ntx5tuuwkzarrmqzdmk4kzdqny

Common Sense Computing: From the Society of Mind to Digital Intuition and beyond [chapter]

Erik Cambria, Amir Hussain, Catherine Havasi, Chris Eckl
2009 Lecture Notes in Computer Science  
This paper presents an overview of past, present and future efforts of the AI community to give computers the capacity for Common Sense reasoning, from Minsky's Society of Mind to Media Laboratory's Digital  ...  And why is it so important for the technological evolution of humankind?  ...  While the first level keeps a copy of the facts in the uniform user language, the second level keeps its own copy in different languages and data structures suitable to be manipulated by specialized inference  ... 
doi:10.1007/978-3-642-04391-8_33 fatcat:hezzeepntjgurdtm6rtxoixzz4

The DARPA High-Performance Knowledge Bases Project

Paul R. Cohen, Robert Schrag, Eric K. Jones, Adam Pease, Albert Lin, Barbara Starr, David Gunning, Murray Burke
1998 The AI Magazine  
The evaluation of the constituent technologies centers on two challenge problems, in crisis management and battlespace reasoning, each demanding powerful problem solving with very large knowledge bases  ...  Questions also can be entered in natural language. START and the TextWise component accept natural language queries and then attempt to answer the questions.  ...  The CYC inference engine comprises an epistemological and a heuristic level. The epistemological level is an expressive nth-order logical language with clean formal semantics.  ... 
doi:10.1609/aimag.v19i4.1423 dblp:journals/aim/CohenSJPLSGB98 fatcat:je5iyiv3zrcgrnee5w4asydnou

Collecting commonsense experiences

Push Singh, Barbara Barry
2003 Proceedings of the international conference on Knowledge capture - K-CAP '03  
We built OMEX to gather descriptions and explanations of everyday, 'common sense' experiences from volunteer contributors distributed across the Internet.  ...  Humans naturally share knowledge by telling stories.  ...  , Glorianna Davenport for her support and for sharing her expertise in interactive story construc-tion, and Marvin Minsky for encouraging us to build a database of stories for commonsense reasoning.  ... 
doi:10.1145/945649.945668 fatcat:wxsoykxecjgdjaie4ut4r2p2dy

Collecting commonsense experiences

Push Singh, Barbara Barry
2003 Proceedings of the international conference on Knowledge capture - K-CAP '03  
We built OMEX to gather descriptions and explanations of everyday, 'common sense' experiences from volunteer contributors distributed across the Internet.  ...  Humans naturally share knowledge by telling stories.  ...  , Glorianna Davenport for her support and for sharing her expertise in interactive story construc-tion, and Marvin Minsky for encouraging us to build a database of stories for commonsense reasoning.  ... 
doi:10.1145/945645.945668 dblp:conf/kcap/SinghB03 fatcat:qbpsvjt7czgwlebldalc2vlbbu
« Previous Showing results 1 — 15 out of 785 results