Filters








73,872 Hits in 3.9 sec

Partially distribution-free learning of regular languages from positive samples

Alexander Clark, Franck Thollard
2004 Proceedings of the 20th international conference on Computational Linguistics - COLING '04   unpublished
We then present a simple learning algorithm for regular languages, and a self-contained proof that it learns according to this partially distribution free criterion.  ...  Efficient algorithms that can reliably learn these languages, and which must in realistic applications only use positive samples, are necessary.  ...  In a distribution-free setting this is not learnable from positive and negative samples, nor a fortiori from positive samples alone.  ... 
doi:10.3115/1220355.1220368 fatcat:3zyq54fb2vbjvbkpkohyrjp6zm

PAC Learning of Some Subclasses of Context-Free Grammars with Basic Distributional Properties from Positive Data [chapter]

Chihiro Shibata, Ryo Yoshinaka
2013 Lecture Notes in Computer Science  
This paper shows that several subclasses of contextfree languages that are known to be exactly learnable with membership queries by distributional learning techniques are pac learnable from positive data  ...  In recent years different interesting subclasses of cfls have been found to be learnable by techniques generically called distributional learning.  ...  Clark [2] has shown that unambiguous nts languages are pac learnable from partially distribution-free positive data only based on distributional learning techniques.  ... 
doi:10.1007/978-3-642-40935-6_11 fatcat:fkr3eznpxvhttei6tl3h7pio5e

Grammatical Inference in Software Engineering: An Overview of the State of the Art [chapter]

Andrew Stevenson, James R. Cordy
2013 Lecture Notes in Computer Science  
examining the sentences of an unknown language.  ...  Software engineering can also benefit from grammatical inference.  ...  It is a context-free grammar with positive samples only, and Gold proved learning a superfinite language in the limit from positive-only samples is impossible [24] .  ... 
doi:10.1007/978-3-642-36089-3_12 fatcat:3qp3xzhhqjgwdhguesrjnvotra

Ten Open Problems in Grammatical Inference [chapter]

Colin de la Higuera
2006 Lecture Notes in Computer Science  
They cover the areas of polynomial learning models, learning from ordered alphabets, learning deterministic Pomdps, learning negotiation processes, learning from context-free background knowledge.  ...  We propose 10 different open problems in the field of grammatical inference. In all cases, problems are theoretically oriented but correspond to practical questions.  ...  Work with Henning Fernau on polynomial learning is where the ideas in section 3 come from. Philippe Jaillon gave me the initial ideas for the negotiation problem in section 9. Discussions with  ... 
doi:10.1007/11872436_4 fatcat:5snm4lpumbhw5e7ffh5vwxzhum

A survey of grammatical inference in software engineering

Andrew Stevenson, James R. Cordy
2014 Science of Computer Programming  
examining the sentences of an unknown language.  ...  Software engineering can also benefit from grammatical inference.  ...  It is a context-free grammar with positive samples only, and Gold proved learning a superfinite language in the limit from positive-only samples is impossible [34] . while limit > a do begin if a > max  ... 
doi:10.1016/j.scico.2014.05.008 fatcat:xwasotc745ekbhaoq2n43vrufm

A bibliographical study of grammatical inference

Colin de la Higuera
2005 Pattern Recognition  
The field of grammatical inference (also known as grammar induction) is transversal to a number of research areas including machine learning, formal language theory, syntactic and structural pattern recognition  ...  The goal of this paper is to introduce a certain number of papers related with grammatical inference.  ...  An unknown distribution over all possible examples exists, and examples are sampled under this distribution. Learning is done from this sample, and the result is tested under the same distribution.  ... 
doi:10.1016/j.patcog.2005.01.003 fatcat:62qwskiqcvddjobakbdshwebqq

1. Formal grammar and information theory: together again? [chapter]

Fernando Pereira
2002 Current issues in linguistic theory  
of language by counting occurrences of linguistic events in very large bodies of text and speech.  ...  Zellig Harris had advocated a close alliance between grammatical and information-theoretic principles in the analysis of natural language, and early formal-language theory provided another strong link  ...  Generalization While Harris discussed the functional role of distributional regularities in language, he proposed no speci c mechanisms by which language users could take advantage of those regularities  ... 
doi:10.1075/cilt.229.05per fatcat:ac7rl72jzzf5fmdc6ax6zc5gb4

LANGUAGE LEARNING, POWER LAWS, AND SEXUAL SELECTION

TED BRISCOE
2006 The Evolution of Language  
The corollary, however, is that rare unpredictable properties of language which do not follow from some regularity manifest during the learning period should be unstable and, therefore, rarely observed  ...  mean that can be accurately estimated from a representative sample of the population.  ... 
doi:10.1142/9789812774262_0003 fatcat:chvm3nh4qbb3nf3aata2ligxwu

Language learning, power laws, and sexual selection

Ted Briscoe
2007 Mind & Society  
The corollary, however, is that rare unpredictable properties of language which do not follow from some regularity manifest during the learning period should be unstable and, therefore, rarely observed  ...  mean that can be accurately estimated from a representative sample of the population.  ... 
doi:10.1007/s11299-007-0040-8 fatcat:z2sp5utuavha3nmzaswdohowue

Editors' Introduction [chapter]

Sanjay Jain, Rémi Munos, Frank Stephan, Thomas Zeugmann
2013 Lecture Notes in Computer Science  
He also studied the learnability of regular languages and context-free languages; a sample result, obtained in collaboration with Franck Thollard, is that the class of regular languages can be PAC-learned  ...  In his invited talk Towards General Algorithms for Grammatical Inference, Alexander Clark deals with the learning of context-free languages and multiple context-free languages.  ...  He also studied the learnability of regular languages and context-free languages; a sample result, obtained in collaboration with Franck Thollard, is that the class of regular languages can be PAC-learned  ... 
doi:10.1007/978-3-642-40935-6_1 fatcat:pchrsvhjezfbvh6dfplqhxhgcy

Learning deterministic regular expressions for the inference of schemas from XML data

Geert Jan Bex, Wouter Gelade, Frank Neven, Stijn Vansummeren
2008 Proceeding of the 17th international conference on World Wide Web - WWW '08  
Unfortunately, there is no algorithm capable of learning the complete class of deterministic regular expressions from positive examples only, as we will show.  ...  Inferring an appropriate DTD or XML Schema Definition (XSD) for a given collection of XML documents essentially reduces to learning deterministic regular expressions from sets of positive example words  ...  Most of the learning of regular languages from positive examples in the computational learning community is directed towards inference of automata as opposed to inference of regular expressions [5, 43  ... 
doi:10.1145/1367497.1367609 dblp:conf/www/BexGNV08 fatcat:bqs6npqyi5eaxlzv5n3ktgb6di

Learning Deterministic Regular Expressions for the Inference of Schemas from XML Data

Geert Jan Bex, Wouter Gelade, Frank Neven, Stijn Vansummeren
2010 ACM Transactions on the Web  
Unfortunately, there is no algorithm capable of learning the complete class of deterministic regular expressions from positive examples only, as we will show.  ...  Inferring an appropriate DTD or XML Schema Definition (XSD) for a given collection of XML documents essentially reduces to learning deterministic regular expressions from sets of positive example words  ...  Most of the learning of regular languages from positive examples in the computational learning community is directed towards inference of automata as opposed to inference of regular expressions [5, 43  ... 
doi:10.1145/1841909.1841911 fatcat:hre7agfyuzhudl3xwlaxxd4xg4

Formal grammar and information theory: together again?

F. Pereira
2000 Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences  
of language by counting occurrences of linguistic events in very large bodies of text and speech.  ...  Zellig Harris had advocated a close alliance between grammatical and information-theoretic principles in the analysis of natural language, and early formal-language theory provided another strong link  ...  in the study of language that most of my work derives from.  ... 
doi:10.1098/rsta.2000.0583 fatcat:pfm2cu4eargphjxrdieln5auti

Neuro-Symbolic Program Synthesis [article]

Emilio Parisotto, Abdel-rahman Mohamed, Rishabh Singh, Lihong Li, Dengyong Zhou, Pushmeet Kohli
2016 arXiv   pre-print
Given a set of input-output examples, these architectures are able to learn mappings that generalize to new test inputs.  ...  We demonstrate the effectiveness of our approach by applying it to the rich and complex domain of regular expression based string transformations.  ...  The semantics of position logic (r, k, Start) is to return the Start of k th match of r in v from the beginning (if k > 0) or from the end (if k < 0).  ... 
arXiv:1611.01855v1 fatcat:osn7netvtnehpcl7l4n2ryl6o4

Learning Languages with Help [chapter]

Christopher Kermorvant, Colin de la Higuera
2002 Lecture Notes in Computer Science  
We present in this paper the possibility of learning when presented with additional information such as the knowledge that the hidden language belongs to some known language, or that the strings are typed  ...  Grammatical inference consists in learning formal grammars for unknown languages when given learning data. Classically this data is raw: strings that belong to the language or that do not.  ...  In this setting the learner is asked to learn from a learning sample, i.e. a finite set of strings, each string labeled by '+' if the string is a positive instance of the language (an element of L), or  ... 
doi:10.1007/3-540-45790-9_13 fatcat:adbjrahojfejxieqmglom6vnay
« Previous Showing results 1 — 15 out of 73,872 results