
	Where results make sense

Topic: Natural language understanding

Related Topics

Natural language processing

HAL 9000

Classical Music

In the News (Fri 25 Dec 09)

Northern Trust

Marvin Harrison

Peter Chernin

Gary Locke

Match Play

Penelope Cruz

Mickey Rourke

AR Rahman

Danny Boyle

Hugh Jackman

	Natural language processing - Wikipedia, the free encyclopedia
		Natural language understanding is sometimes referred to as an AI-complete problem, because natural language recognition seems to require extensive knowledge about the outside world and the ability to manipulate it.
		The grammar for natural languages is not unambiguous, i.e.
		Statistical natural language processing uses stochastic, probabilistic and statistical methods to resolve some of the difficulties discussed above, especially those which arise because longer sentences are highly ambiguous when processed with realistic grammars, yielding thousands or millions of possible analyses.
	en.wikipedia.org /wiki/Natural_language_understanding (714 words)

	Modelling for Natural Language Understanding
		The benefit is a potentialisation of the model, having access to a natural language input (analyser) and output (generator), as well as potentialisation of the NLU system, being grounded on a solid source of knowledge, for the task of generating its dictionaries and concept definitions.
		This is a true challenge for NLU: to reverse the process where the modelling phase precedes the natural language processing phase, and to grasp additional knowledge from the unlimited corpus of written documents.
		In order for natural language to take in additional knowledge, it is necessary to build a deep and robust model of the domain, with good coherence and stability, and which is able to resist inconsistencies and ambiguities.
	mbi.dkfz-heidelberg.de /helios/doc/nlp/Baud93a.html (2984 words)

	Understanding Natural Language with Diagrams
		Natural language is a versatile means of communication, but it is difficult to describe complex spatial relationships using natural language.
		The process of understanding text and diagram together must be opportunistic: it is important to use all the clues that are available, but it is not possible to predict which clues will be present for a particular problem or what order of interpretation will cause all the pieces to fall into place.
		In order to correctly understand the problem, the friction value from the text must be associated in the problem model with the contact relation between block and plane that was derived from the diagram.
	www.cs.utexas.edu /users/novak/aaai90.html (3451 words)

	Allen 1995: Natural Language Understanding - Introduction (Site not responding. Last check: 2007-11-06)
		To be an understanding system, the speech recognizer would need to feed its input to a natural language understanding system, producing what is often called a spoken language understanding system.
		A natural language-system must use considerable knowledge about the structure of the language itself, including what the words are, how words combine to form sentences, what the words mean, how word meanings contribute to sentence meanings, and so on.
		Of course, if this were a spoken language application, the words would not be the final input and output, but rather would be the output of a speech recognizer and the input to a speech synthesizer, as appropriate.
	www.uni-giessen.de /~g91062/Seminare/gk-cl/Allen95/al199501.htm (7458 words)

	Let's meet the users with Natural Language Understanding
		Natural Language Understanding is a research area which aims at developing a set of basic tools for handling free texts, particularly in the medical environment.
		On the natural language side, French and English dictionaries and a corresponding language analyzer have been produced by the author's group {ref3} within the framework of the HELIOS consortium {ref7}.
		NLU systems are strongly dependent on medical linguistic knowledge bases, in particular on the different European language lexicons.
	mbi.dkfz-heidelberg.de /helios/doc/nlp/Baud93b.html (2687 words)

	PARC Understanding Natural Language (Site not responding. Last check: 2007-11-06)
		They are tackling the core challenge of creating standardized, canonical representations of the meaning of natural language text, regardless of how that meaning is expressed.
		The inherent ambiguity of natural language means that parsing and semantic algorithms often generate large numbers of alternative interpretations.
		It is built on the Xerox Linguistic Environment, a proprietary set of PARC technologies for natural language processing.
	parc.com /research/projects/natural_lang/nat_lang_understanding.html (501 words)

	NL Understanding & Generation
		A collection of publications from the HealthDoc Project ("What is needed is a natural language generation system for the production of tailored health-information and patient-education documents, that would, on demand, customize a 'master document' to the needs of a particular individual.
		Natural Language Understanding Lecture Notes from Professors Tomás Lozano-Pérez and Leslie Kaelbling's Spring 2003 course: Artificial Intelligence.
		The inherent ambiguity of natural language means that parsing and semantic algorithms often generate large numbers of alternative interpretations." Be sure to see their links to related information, publications, and research groups.
	www.aaai.org /AITopics/html/nlunder.html (2149 words)

	CFP: Real-world Natural Language Understanding, FLAIRS-96
		Language processing is situated in the world of real texts, allowing RNLU to leverage off certain characteristics of such texts which provide a basis for scale-up.
		Exactly what this level needs to be varies from task to task, but simple syntactic parsing or keyword-based information extraction is usually insufficient for real-world natural language communication at a level comparable to human language abilities.
		RNLU exploits a range of information present in natural language texts, as well as background information known to the author and reader, in order to achieve a suitable depth of comprehension of the text.
	documents.cfar.umd.edu /newsgroups/miscarchive/msg00024.html (534 words)

	Natural Language Processing
		Natural Language Lecture Slides and Accompanying Transcripts from Professors Tomás Lozano-Pérez and Leslie Kaelbling's Spring 2003 course: Artificial Intelligence.
		Not only does the ability to use and understand natural language seem to be a fundamental aspect of human intelligence, but also its successful automation would have an incredible impact on the usability and effectiveness of computers themselves.
		Understanding natural language involves much more than parsing sentences into their individual parts of speech and looking those words up in a dictionary.
	www.aaai.org /AITopics/html/natlang.html (3572 words)

	Natural language processing - Open Encyclopedia (Site not responding. Last check: 2007-11-06)
		An example of such a constructed language that could be used for higher order human/computer communication is lojban.
		Statistical natural language processing uses stochastic methods to solve some of the problems discussed above, notably the ambiguity problems.
		These methods often involve the use of corpora and Markov models.
	open-encyclopedia.com /Natural_language_understanding (637 words)

	Understanding NL Summary.html
		For regular and context-free grammars, there are practical parsing algorithms to determine whether or not a given string is an element of the language, and if so, to assign to it a syntactic structure in the form of a derivation tree.
		Process of recognizing whether a string belongs to the language of the DCG becomes equivalent to proving a theorem in logic.
		understanding plan-based stories involved descerning the goals of the actor and the methods by which the actor chooses to fulfill the goals.
	www-ksl.stanford.edu /people/vemuri/quail/summaries/understanding-nl-summary.html (3054 words)

	Natural Language Understanding (Site not responding. Last check: 2007-11-06)
		The objective of a natural language understanding unit is to extract all the information from an utterance that are relevant for a specific application.
		An interesting approach to natural language understanding can be derived from the field of statistical machine translation.
		In this context, the input sentence given in a natural language forms the source language, and the sequence of concepts forms the target language.
	www-i6.informatik.rwth-aachen.de /web/Research/NLUnderstanding_frame.html (261 words)

	Allen 1995: Natural Language Understanding - Preface (Site not responding. Last check: 2007-11-06)
		The primary goal of this book is to provide a comprehensive, in-depth description of the theories and techniques used in the field of natural language understanding.
		As a reference source, it can be used by researchers in areas related to natural language, by developers building natural language systems, and by individuals who are simply interested in how computers can process language.
		Work in natural language understanding requires background in a wide range of areas, most importantly computer science, linguistics, logic, psycholinguistics, and the philosophy of language.
	www.uni-giessen.de /~g91062/Seminare/gk-cl/Allen95/al1995pr.htm (455 words)

	Active Skim View of: Integration of Speech with Natural Language Understanding
		The standard model of speech and natural language ' + 'integration can be implemented by N-best filtering, in which the recognizer simply produces an ordered list of hypotheses, and the natural language processor ' + 'chooses the first one on the list that can be completely parsed and interpreted.
		For instance, for the CMU system the rate of understanding error increased ' + 'by only 4.7 percent of all utterances when a verified transcription of the test utterances was replaced by speech recognizer output, even though 28.9 percent ' + 'of the recognizer outputs contained at least one word recognition error.
		Page 262 recognition and natural language understanding system ' + 'was presented with the digitized speech signal for the same utterances, and (3) the percentage of queries for which the speech recognition component of ' + 'the system made at least one word recognition error in transcribing the utterance.
	www.nap.edu /nap-cgi/skimit.cgi?isbn=0309049881&chap=254-272 (10489 words)

	Knowledge Acquisition for Natural Language Understanding
		This knowledge engineering bottleneck remains one of the biggest problems in designing and building natural language systems and promises only to become worse as natural language systems attempt to understand a wider variety of texts, to produce more complex summaries of the text, and to extract knowledge directly from text in a variety of forms.
		The objective of this research is to address this knowledge engineering bottleneck for natural language processing (NLP) systems by developing algorithms that use inductive learning techniques to allow NLP systems to bootstrap their own knowledge bases directly from text.
		We plan to use natural language learning techniques as the central component in a system that will allow end-users to train information extraction systems for their own domains in a matter of days and without the intervention of NLP system developers.
	cslu.cse.ogi.edu /nsf/isgw97/reports/cardie.html (1223 words)

	Brown CS - CS241 (Site not responding. Last check: 2007-11-06)
		This course covers statistical methods for learning a natural language and applying the knowledge to specific tasks.
		Topics include: entropy and cross entropy of a language, hidden Markov models, Viterbi algorithm, forward-backward algorithm, trigram models, part-of-speech tagging, probabilistic context-free parsing, inside-outside algorithm, learning probabilistic context-free grammars, statistical models of syntactic disambiguation, statistical anaphora resolution, deriving semantic word classes from statistical properties, and word-sense disambiguation.
		Grading is based primarily on the project, and secondarily on the two in-class, 40 minute, exams.
	www.cs.brown.edu /courses/cs241 (137 words)

	Review: COMMUNICATION FAILURE IN DIALOGUE:IMPLICATIONS FOR NATURAL LANGUAGE UNDERSTANDING (Site not responding. Last check: 2007-11-06)
		The idea of this article was to emphess some of the theoritical and technical issues invoved in getting computers to engage in non-spocken natural language dialogue with a user and in addition, the issue of vigorousness in the natural langues communication.
		The paper has put two main assumption which the are (a) The best medium for understnding natural languages understanding is dialogue.
		There should be some understanding of the terminology, The term discourse and dialogue are used inter changably, but it is very useful to distingush between extended monologue, both spoken and textual, and true dialogue involving one or more participants.
	www.scism.sbu.ac.uk /inmandw/review/nlp/review/rev6205.html (4083 words)

	.NET Undocumented: Natural Language Understanding
		There is an area of natural language processing called semantics, which takes a grammatical parse tree of a sentences and converts into an internal semantic representation for reasoning.
		Part of the problem is that natural language support is a time-consuming and specialized endeavor, especially if multiple languages are to be supported.
		Posted by: Lawrence Oluyede at June 28, 2004 08:52 AM Language is so innately human that people are weirded out by the idea that it can be parsed analytically, or that people are intelligent machines.
	wesnerm.blogs.com /net_undocumented/2004/06/natural_languag.html (691 words)

	Amazon.co.uk: Books: Natural Language Understanding (Site not responding. Last check: 2007-11-06)
		With the first edition of Natural Language Understanding, James Allen established a new standard for texts on natural language understanding.
		Natural Language Understanding, Second Edition builds on the effective framework of the first edition and enhances it by covering the most recent developments as well as discussing the current direction of research in this field today.
		Outlines the basics of speech recognition in a new appendix on spoken language understanding.
	www.amazon.co.uk /exec/obidos/ASIN/0805303340 (746 words)

	Natural Language Understanding (2nd Edition)
		The student naturally recoils in horror, but unless she reads a prolog-oriented book on NLP, she would never know how much easier DCGs are to program than ATNs or the bottom-up parsing methods which Allen goes on to expostulate.
		Also, a few chapters on natural language generation would be nice, as well as discussions on dialogue.
		"Natural Language Understanding" was the first NLP text I read (for a summer job), and I've always referred to it first for its balance of formal and practical considerations.
	www.configuration-management.org /configuration-management-books/isbn0805303340.html (863 words)

	Active Skim View of: Models of Natural Language Understanding
		Some aspects of language understanding seem tantalizingly similar to problems that have been solved (or at least attacked) in speech recognition, but other aspects seem to emphasize differences that may never allow the same solutions to be used for both problems.
		(which combine speech recognition with language understanding), language generation, message processing (the term used for systems that deal with bodies of written language in a noninteractive way, including document indexing and retrieval, text classification, and contents scanning, which is also called data extraction)
		achieve an understanding error rate of about 6 percent, which appears to be quite close to the threshold of real utility for applications.
	www.nap.edu /nap-cgi/skimit.cgi?isbn=0309049881&chap=238-253 (726 words)

	[No title]
		In some sense, natural language is at the center of human intelligence.
		Query language expression is executed on the database to produce the answer to the request.
		Understanding consists in the procedures executed as a result of an input.
	www.cc.gatech.edu /computing/classes/cs3361_96_spring/Fall95/Notes/natural-language-understanding.html (4664 words)

	Dr. Fernando Gomez
		Fernando Gomez's research covers a range of issues in natural language understanding including parsing, semantic interpretation, knowledge acquisition, knowledge representation and problem-solving.
		The main effort in semantic interpretation is directed towards achieving it on a large scale as required in the understanding of encyclopedic texts.
		This constructive process is done by means of integration rules, which build the deep structure on the basis of the semantics of the logical forms of the sentences and on the deep structure under construction.
	www.cs.ucf.edu /~gomez (1241 words)

	Homer: Natural Language Understanding (Site not responding. Last check: 2007-11-06)
		Homer's architecture incorporates a natural language parser and semantic interpreter system
		Natural language sentences are converted using state transition semantics in order for the parsed language to be used for planning
		The functional goals for natural language understanding are limited, one is expected to talk to Homer as one would talk to a young child
	ai.eecs.umich.edu /cogarch3/Homer/Homer_NLUnder.html (78 words)

	Statistical natural language understanding using hidden clumpings (US5987404)
		The key notion is that there are "strings" of words in the natural language, that correspond to a single semantic concept.
		System for processing natural language including identifying grammatical rule and semantic concept of an undefined word
		C. Suen, "n-Gram Statistics for Natural Language Understand and Text Processing", IEEE Trans.
	www.delphion.com /details?pn=US05987404__ (332 words)

	SRI Gemini System (Site not responding. Last check: 2007-11-06)
		Natural-language research under SRI International's project on Improved Spoken-Language Understanding is focused on the development of Gemini, a natural-language parsing and semantic interpretation system based on unification grammar.
		Optional modules in Gemini provide robustness through a novel technique for detecting and correcting speech repairs, and by heuristically combining interpretations of grammatical fragments into an overall interpretation for the utterance, in cases where the Gemini grammar and lexicon do not provide a single complete analysis.
		Gemini has also been used as part of a language model to increase speech recognition accuracy.
	www.ai.sri.com /natural-language/projects/arpa-sls/nat-lang.html (250 words)

Try your search on: Qwika (all wikis)