Factbites
 Where results make sense
About us   |   Why use us?   |   Reviews   |   PR   |   Contact us  

Topic: AI (disambiguation)


In the News (Wed 7 Jan 09)

  
 [No title]
Although her original assumption was that much disambiguation could be accomplished based on paragraph topic, she found that half of the disambiguation was actually accomplished using fixed phrase and syntactic information, while the other half was accomplished using commonsense reasoning.
Disambiguation was accomplished by selecting the sense of the target word whose signature contained the greatest number of overlaps with the signatures of neighboring words in its context.
The notion of disambiguating senses based on domain is implicit in various AI based approaches, such as Schank's script approach to natural language processing (Schank and Abelson, 1977), which matched words to senses based on the context or "script" activated by the general topic of the discourse.
aune.lpl.univ-aix.fr /pub/multext/cl/idevero.txt   (16819 words)

  
 WORD SENSE DISAMBIGUATION
The aim in supervised disambiguation is to build a classifier which correctly classifies new cases based on their context of use.
The basic inference in thesaurus-based disambiguation is that semantic categories of the words in a context determine the semantic category of that context as a whole.
Disambiguation is done by computing the semantic similarity between words and applying the heuristic rules based on this similarity.
www.denizyuret.com /students/bmutlum/thesis.htm   (7493 words)

  
 AI:
AI divides roughly into two schools of thought: Conventional AI and Computational Intelligence (CI), also sometimes referred to as Synthetic Intelligence to highlight the differences.
The first working AI programs were written in 1951 to run on the Ferranti Mark I machine of the University of Manchester: a draughts-playing program written by Christopher Strachey and a chess-playing program written by Dietrich Prinz.
The birthdate of AI is generally considered to be July 1956 at the Dartmouth Conference, where many of these people met and exchanged ideas.
winelib.com /wiki/AI   (1974 words)

  
 Ai - Wikipedia, the free encyclopedia
Emperor Ai of Jin, a Jin Dynasty (265-420) emperor
Merneferre Ai, an Ancient Egyptian ruler of the thirteenth dynasty of Egypt.
Ai Toyon, the Yakut god of light, usually depicted as an eagle perched atop the "world tree".
en.wikipedia.org /wiki/AI_(disambiguation)   (581 words)

  
 Logic and Artificial Intelligence (Stanford Encyclopedia of Philosophy)
AI has drawn on many research methodologies; the value and relative importance of logical formalisms is questioned by some leading practitioners, and has been debated in the literature from time to time.
Although for many AI logicists, the goal of action formalisms is to illuminate an important aspect of common sense reasoning, most of their research is uninformed by an important source of insights into the common sense view of time—namely, natural language.
AI applications deal with with knowledge in the form of stored representations, and the tradition in AI with which we are concerned here thinks of reasoning as the manipulation of symbolic representations.
plato.stanford.edu /entries/logic-ai   (16964 words)

  
 eXtended WordNet
The glosses are represented by the tag that inlcludes the synonym set, the text of the gloss, the parse tree, the logic form tranformation and the semantic disambiguation of the gloss.
The semantic disambiguation part is marked by the tag and includes words represented by the tag and punctuation represented by the tag.
The second phase is the effective disambiguation that consists of assigning to each open class word the correct sense using its part of speech.
xwn.hlt.utdallas.edu /wsd.html   (1218 words)

  
 Word Sense Disambiguation Book - Foreword
The first generations of AI researchers found it easy to construct examples of ambiguities whose resolution seemed to require vast knowledge and deep understanding of the world and complex inference on this knowledge; for example, Pharmacists dispense with accuracy.
The disambiguation problem was, in a way, nothing less than the artificial intelligence problem itself.
In my own early work (Hirst 1987), restrictions on communication between disambiguating processes arose from two competing principles: any particular word or structural cue for disambiguation has quite a limited sphere of influence, and yet almost anything in a text or discourse is potentially a cue for disambiguation (cf.
www.wsdbook.org /foreword.html   (702 words)

  
 directopedia : Directory : Computers : Artificial Intelligence
Although AI has a strong science fiction connotation, it forms a vital branch of computer science, dealing with intelligent behavior, learning and adaptation in machines.
AI systems are now in routine use in economics, medicine, engineering and the military, as well as being built into many common home computer software applications and video games.
In science fiction AI is commonly portrayed as an upcoming power trying to overthrow human authority as in HAL 9000, Skynet, Colossus and The Matrix or as service humanoids like C-3PO, Data, the Bicentennial Man, the Mechas in A.I. or Sonny in I, Robot.
www.directopedia.org /directory/Computers-Artificial_Intelligence.shtml   (1796 words)

  
 Teaching AI Methods to Children
As we can see, these AI principles and methods are quite general since they are knowledge-independent, capable of solving various problems of the same kind.
We believe that teaching AI for improving children's high-level thinking abilities is a fascinating new application of AI in education.
The AI principles and methodologies are also quite concrete, since they could be illustrated in detailed steps, just as computer algorithms, through thinking games and puzzles.
www.csd.uwo.ca /faculty/ling/iccs99-html/node4.html   (747 words)

  
 Smart Software: AI
I first took an AI course at Columbia University while I was in high school, and was completely entralled.
Unfortunately, AI in the 1980s was associated with numerous project failures and gained a bad reputation.
I am in the symbolic AI camp, though I do see statistical approaches as complementary in the areas of disambiguation and prediction.
wesnerm.blogs.com /net_undocumented/2004/06/ai.html   (352 words)

  
 URCS AI Technical Reports
Further, we propose that word sense disambiguation programs that use WordNet as their dictionary may be evaluated with respect to this compaction, for a better indicator of performance.
We present a framework for corpus-based syntactic disambiguation which pulls together the well-foundedness of the traditional approaches and the scalability of the corpus-based approaches.
None of these interpretive procedures is especially concerned with `scope disambiguation,' but the result of these inferences is that relations of contextual dependency such as anaphoric reference or presuppositionality become part of the common ground; the scope preferences observed in the literature reflect these relations of dependency.
www.cs.rochester.edu /trs/ai-trs.html   (17506 words)

  
 An Overview of Webmind AI   (Site not responding. Last check: 2007-10-16)
Webmind AI Engine Overview, is a multi-modular AI system, which achieves general intelligence through the emergent structures and dynamics that arise when many specialized mind-modules are integrated in a suitable common framework.
An AI system should be able to focus its global attention on one set of nodes very tightly, rather than in a diffusive way as promoted by ordinary psynet dynamics.
For a single example, consider the problem of semantic disambiguation: When entering a word with many senses into the psynet, it must be decided which sense of the word is intended (or, in situations of subtle ambiguity, to what extent each sense of the word is intended).
www.bugaj.com /pubs/WebmindOverview.html   (14009 words)

  
 ai - OneLook Dictionary Search
AI : Compact Oxford English Dictionary [home, info]
AI, AI : Dorland's Illustrated Medical Dictionary [home, info]
Phrases that include ai: ai an, ai apaec, ai velae star, shoujo ai, vbe ai, more...
onelook.com /?w=ai   (590 words)

  
 Parser Mind-Module for the Breakthrough in Artificial Intelligence of 7 June 2006
Parsing in the AI will be like parsing in human infancy.
Suddenly the IQ of the AI is set to burgeon as the functionality of the Parser module burgeons.
AI Debugger program may shed some light in general on how to debug
mind.sourceforge.net /parser.html   (2141 words)

  
 Artificial intelligence - Wikipedia, the free encyclopedia
Artificial intelligence (AI) can be defined as intelligence exhibited by an artificial (non-natural, manufactured) entity.
AI is studied in overlapping fields of computer science, psychology and engineering, dealing with intelligent behavior, learning and adaptation in machines, generally assumed to be computers.
As such, the study of AI has also become an engineering discipline, focused on providing solutions to real life problems, software applications, traditional strategy games like computer chess and other video games.
en.wikipedia.org /wiki/Artificial_intelligence   (1990 words)

  
 Artificial Intelligence (Computers) - Chainki   (Site not responding. Last check: 2007-10-16)
AI Topics is a web site designed to provide online access to introductory resources concerning artificial intelligence and its many dimensions.
Also, it attempts to showcase leading technologies in AI and related fields.
Free software and materials of general interest to AI researchers, educators, students, and practitioners.
en.chainki.org /index.php?title=Artificial_Intelligence_(Computers)   (388 words)

  
 CS5604, Unit KB
The area of Knowledge-Based Information (KBIR) is an active one, with IR researchers trying to apply various AI schemes to improve IR systems, and with AI researchers trying to extend their systems and apply their methods in the domain of IR.
Fourth, if the above occur, the system may use AI methods to match the representations, yielding some type of ranking or selection that considers the uncertainty and the statistical data that are available.
In the AI field, one key area is natural language processing (NLP) and the related area of computational linguistics.
ei.cs.vt.edu /~cs5604/f96/U-KB/U-KB.html   (1988 words)

  
 Labeled, weighted directed hyperedges
All of these are things with which the author and his implementation team have direct experience; they were implemented in the Webmind AI Engine (though 5, NLP querying, was only implemented to a limited extent).
In dealing with the Novamente AI Engine, we often find it handy to have other programs produce length nmshell scripts and then load these scripts into the Novamente AI Engine; it seems likely that this will be a handy way of interacting with OE as well.
Automated disambiguation may be done (and was done in WAE) as follows: When a new named knowledge item is added, a judgment is made regarding its similarity to the existing knowledge item with the same name.
www.goertzel.org /papers/ir/OntologyEngineSketch_June23_2002.htm   (3595 words)

  
 AI Magazine Special Issue on Empirical Natural Language Processing
This article is an introduction to some of the emerging research in the application of corpus-based learning techniques to problems in semantic interpretation.
Machine translation of human languages (for example, Japanese, English, Spanish) was one of the earliest goals of computer science research, and it remains an elusive one.
Like many AI tasks, trans-lation requires an immense amount of knowledge about language and the world.
www.cs.utexas.edu /users/mooney/aimag.html   (526 words)

  
 AI has been solved
and of supporting the AI code as if were not freeware but shareware.
AI book as an AI textbook is a memetic device for upsetting the
beyond the mainstream currents of academic AI, but a purported AI textbook poses a clear and present disruption of the status quo.
mentifex.virtualentity.com   (425 words)

  
 CS 288: An AI Approach to NLP   (Site not responding. Last check: 2007-10-16)
Other topics include lexical and grammatical disambiguation, the computational use non-literal language, and language acquisition.
The course covers a variety of approaches to these fundamental problems, but also examines practical techniques that implement partial solutions to problems such as lexical disambiguation and parsing, and some applications of these solutions to tasks such as information retrieval and machine translation.
While extensive familiarity with Artificial Intelligence or linguistics is not presumed, some background in AI is helpful.
www.cs.berkeley.edu /~wilensky/cs288/description.html   (211 words)

  
 Qwika - similar:Knowledge_representation
Artificial intelligence (AI) is defined as intelligence exhibited by an artificial entity.
Although AI has a strong science fiction connotation, it forms a vital branch of computer sci...
Genetic programming (GP) is an automated methodology inspired by biological evolution to find computer programs that best perform a user-defined task.
www.qwika.com /rels/Knowledge_representation   (1525 words)

  
 Disambiguation (Dev Diary) - Page 13 - The Lord of the Rings Online(tm): Shadows of Angmar(tm) Forums
I agree that as advanced as AI gaming is now, after a few short weeks players know how to outmanuver monsters.
To exploit the system in ways that would not be possible in RL, or if a live person were behind the monsters actions.
This is a win win situation both for people who like PVP and for players like me who have never seen the allure...until now.
lotro.turbine.com /forums/showthread.php?p=263346#post263346   (1297 words)

  
 AI Qual Summary: Natural Language
Parsing is the "de-linearization" of linguistic input; that is, the use of grammatical rules and other knowledge sources to determine the functions of words in the input sentence.
The systems to be designed were to accept normally spoken sentences in a constrained domain with a 1,000 word vocabulary, and were to respond in reasonable time with less than 10% error.
Important features included concern with the nature of real man-machine discourse, a language definition system for specifying the input language to be understood, techniques for focusing the system's attention on certain aspects of the dialog, top-down process control stressing phrase-level hypothesizing, knowledge representation using partitioned semantic networks, and experimental evaluation of system design parameters.
www.cs.dartmouth.edu /~brd/Teaching/AI/Lectures/Summaries/natlang.html   (5547 words)

  
 COM334: Language Engineering
The historical role of NLP in artificial intelligence (AI) in general, sometimes nearer, sometimes further from the centre: in Japan in it very close to the centre, here further away.
Raskin and Nirenburg have argued (1996) that Dorr's claim is the reverse of Levin's and that she is claiming willy-nilly that syntax determines semantics for the English verb and not vice versa, as Levin certainly seems to intend.
NOTE that these methods of disambiguation can now be more widely applied than just to the dictionary definitions but can be general sense-resolution-in-text mechanisms.
www.dcs.shef.ac.uk /~yorick/le334.html   (10068 words)

  
 job on the web
Protecting human rights worldwide, AI focuses on the release of prisoners of conscience, fair and prompt trials for all political prisoners and the abolition of the death penalty, torture and other...
Artificial intelligence (abbreviated AI, also some times called Synthetic Intelligence) is defined as intelligence exhibited by an artificial...
Lots and lots of pointers to AI resources: intelligent agents, search and game playing, logic and knowledge representation, planning, reasoning with uncertainty, machine learning, natural language...
www.jobangebote-kassel.de /AI.asp   (219 words)

  
 Natural Language Processing
One goal of AI work in natural language is to enable communication between people and computers without resorting to memorization of complex commands and procedures.
Both are just part of the broad field of AI and natural language, along with the cognitive science aspect of using computers to study how humans understand language.
What sets this chatty AI (artificial intelligence) chatbot apart from others is the more it natters, the more it learns.
www.aaai.org /AITopics/html/natlang.html   (4055 words)

  
 AI Foundry
The AI Foundry is a collection of Open Source projects relating to Artificial Intelligence.
Hosted right here on the AI Depot, this gives everyone the opportunity to discuss the member projects and their common goals.
Any Open Source project relating to AI is welcome to join; just email us.
foundry.ai-depot.com   (437 words)

  
 Derek Bridge - Artificial Intelligence - Teaching Materials
Read about the use of AI in games and simulations at John Funge's site.
Another excellent general site is the AI on the Web page that is associated with the best AI textbook available: Stuart Russell's and Peter Norvig's Artificial Intelligence: A Modern Approach (2nd edn.), Prentice Hall, 2003.
This is followed by a presentation on the use of case-based reasoning in AI search.
www.cs.ucc.ie /~dgb/courses/ai/lectures.html   (2389 words)

Try your search on: Qwika (all wikis)

Factbites
  About us   |   Why use us?   |   Reviews   |   Press   |   Contact us  
Copyright © 2005-2007 www.factbites.com Usage implies agreement with terms.