Filters








959 Hits in 3.8 sec

Some Classes of Regular Languages Identifiable in the Limit from Positive Data [chapter]

François Denis, Aurélien Lemay, Alain Terlutte
2002 Lecture Notes in Computer Science  
Parsing Using Probabilistic Grammatical Inference p. 269 Learning of Regular Bi-?  ...  Inferring Subclasses of Regular Languages Faster Using RPNI and Forbidden ConfigurationsTable of Contents provided by Blackwell's Book Services and R.R. Bowker.  ... 
doi:10.1007/3-540-45790-9_6 fatcat:nmlknwqoyfbybhb6rpomqrn7qy

Page 80 of Computational Linguistics Vol. 34, Issue 1 [page]

2008 Computational Linguistics  
Shallow parsing with conditional random fields.  ...  Towards efficient probabilistic HPSG parsing: Integrating semantic and syntatic preference to guide the parsing. In Proceedings of the I[CNLP-04 Workshop “Be >yond Shallow Analyses”, Hainan Island.  ... 

Three studies of grammar-based surface-syntactic parsing of unrestricted English text. A summary and orientation [article]

Atro Voutilainen (Research Unit for Computational Linguistics, University of Helsinki)
1994 arXiv   pre-print
This accuracy suggests the viability of the grammar-based approach to natural language parsing, thus also contributing to the more general debate concerning the viability of probabilistic vs. linguistic  ...  The dissertation addresses the design of parsing grammars for automatic surface-syntactic analysis of unconstrained English text. It consists of a summary and three articles.  ...  However, working with a shallow grammatical representation brought up some new observations.  ... 
arXiv:cmp-lg/9406039v1 fatcat:whf2efy56vcr7i253uqinu6xaa

Position Models and Language Modeling [chapter]

Arnaud Zdziobeck, Franck Thollard
2008 Lecture Notes in Computer Science  
An alternative to this model is the probabilistic automaton.  ...  We propose here to improve the use of this model by restricting the dependency to a more reasonable value.  ...  sentences (e.g character recognition [14] , shallow parsing [18] ).  ... 
doi:10.1007/978-3-540-89689-0_12 fatcat:perwz65gsrbmflpk6hsnyi7o6i

Towards an open software architecture for interleaved knowledge and natural language processing

Marcus Spies
2015 Scientific Publications of the State University of Novi Pazar Series A Applied Mathematics Informatics and mechanics  
Many existing integrations of natural language processing (NLP) and knowledgebased systems build on "shallow" NLP.  ...  Recent progress in NLP, however, has brought "deep" processing features like sentential parsing and semantic dependency analysis to a highly mature level for a substantial set of common spoken languages  ...  As this entire tradition of research basically neglects the grammatical and logical structure of texts, it is also often referred as "shallow NLP", in contrast to "deep NLP".  ... 
doi:10.5937/spsunp1501007s fatcat:ahgcthfenrdurox2cc3haxtfnu

A Genetic Programming Experiment in Natural Language Grammar Engineering [chapter]

Marcin Junczys-Dowmunt
2012 Lecture Notes in Computer Science  
This paper describes an experiment in grammar engineering for a shallow syntactic parser using Genetic Programming and a treebank.  ...  The used genetic operators are described. The performance of the evolved grammar after 1,000 generations on an unseen test set is improved by 2.7 points F-score (3.7 points on the training set).  ...  The shallow parser cannot be easily trained on a treebank using classical grammar extraction methods like the creation of a probabilistic context-free grammar.  ... 
doi:10.1007/978-3-642-32790-2_41 fatcat:r35njsdjljbvjkya5km7glrn7e

Logic-based genetic programming with definite clause translation grammars

Brian J. Ross
2001 New generation computing  
An application using DCTG-GP is described. * 1  ...  DCTG-GP is a genetic programming system that uses definite clause translation grammars.  ...  The experiment involves the grammatical inference of a probabilistic pattern matching language.  ... 
doi:10.1007/bf03037572 fatcat:ybx53tyi5vfy3auf3q4qpqkakm

Robustness beyond shallowness: incremental deep parsing

S. AÏT-MOKHTAR, J.-P. CHANOD, C. ROUX
2002 Natural Language Engineering  
Among those approaches is shallow or partial parsing, which produces minimal and incomplete syntactic structures, often in an incremental way.  ...  We argue that with a systematic incremental methodology one can go beyond shallow parsing to deeper language analysis, while preserving robustness.  ...  Shallow Parsing Shallow parsing is the incomplete grammatical analysis of texts (also called light or partial parsing).  ... 
doi:10.1017/s1351324902002887 fatcat:xoijb6d3jvex7d7x77t5irgshq

Towards the Automatic Acquisition of a Valence Dictionary for Polish [chapter]

Adam Przepiórkowski
2009 Lecture Notes in Computer Science  
We show that the valence dictionary obtained with the use of shallow parsing attains higher quality when it is measured on the basis of a corpus of valence frames, while the dictionary produced with the  ...  This article presents the evaluation of a valence dictionary for Polish produced with the help of shallow parsing techniques and compares those results to earlier results involving deep parsing.  ...  Shallow Parsing The corpus obtained as described in the previous section was shallow parsed with the Spejd (http://nlp.ipipan.waw.pl/Spejd/; [23] ) grammar presented in ch. 8 of [22] , i.e., maximal  ... 
doi:10.1007/978-3-642-04735-0_8 fatcat:jftxsu5n5ndajg4xc32fdhkwnm

A bibliographical study of grammatical inference

Colin de la Higuera
2005 Pattern Recognition  
The goal of this paper is to introduce a certain number of papers related with grammatical inference.  ...  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  ...  Applications Applications based purely on grammatical inference are few, but many use grammatical inference ideas or techniques.  ... 
doi:10.1016/j.patcog.2005.01.003 fatcat:62qwskiqcvddjobakbdshwebqq

Designing Statistical Language Learners: Experiments on Noun Compounds [article]

Mark Lauer
1996 arXiv   pre-print
Both syntactic and semantic analysis of noun compounds are attempted using the proposed architecture.  ...  superficial linguistic elements; and (ii) it explores the development of a mathematical theory to predict the expected accuracy of statistical language learning systems in terms of the volume of data used  ...  There are other probabilistic models of parsing, each varying in the way in which grammatical structure is construed as events.  ... 
arXiv:cmp-lg/9609008v1 fatcat:yipwhts6ybhknmwimhbqrhchv4

State of the art in Computational Linguistics [chapter]

Giacomo Ferrari
2004 Linguistics Today – Facing a Greater Challenge  
the use of some sort of mass-parsing techniques, based on substantial simplifications of traditional parsing.  ...  By "chunking", a text is divided into chunks that may belong to the same phrase (but this is to be verified) while "shallow parsing" implies in any case the attribution of some shallow structure, as it  ... 
doi:10.1075/z.126.09fer fatcat:j6qpxzdy4jfhbj3p4a6pb33z6e

A Shallow Text Processing Core Engine

Gunter Neumann, Jakub Piskorski
2002 Computational intelligence  
In this paper we present 1 sppc, a high-performance system for intelligent extraction of structured data from free text documents. sppc consists of a set of domain-adaptive shallow core components that  ...  The whole approach proved to be very useful for processing free word order languages like German. sppc has a good performance (more than 6000 words per second on standard PC environments) and achieves  ...  Other useful information for inferring grammatical relations is whether the verb is active or passive and the attachment borders of the dependency tree.  ... 
doi:10.1111/0824-7935.00197 fatcat:ggrveuikyfb6no6tbprmji2vcu

Automatic extraction of subcategorization from corpora

Ted Briscoe, John Carroll
1997 Proceedings of the fifth conference on Applied natural language processing -  
In a recent experiment with a wide-coverage parsing system utilizing a lexicalist grammatical framework, Briscoe & Carroll (1993) observed that half of parse failures on unseen test data were caused  ...  This gives us an estimate of the parsing performance that would result from providing a parser with entries built using the system, shown in Figure 5 .  ... 
doi:10.3115/974557.974609 dblp:conf/anlp/BriscoeC97 fatcat:4bw3zd3llfcdtds45f3nfmlnzq

Automatic Extraction of Subcategorization from Corpora [article]

Ted Briscoe, John Carroll (University of Sussex)
1997 arXiv   pre-print
In a recent experiment with a wide-coverage parsing system utilizing a lexicalist grammatical framework, Briscoe & Carroll (1993) observed that half of parse failures on unseen test data were caused  ...  : Shallow PARsing and Knowledge extraction for Language Engineering', and by SERC/EPSRC Advanced Fellowships to both authors.  ... 
arXiv:cmp-lg/9702002v1 fatcat:xqzt2yff2jaanhtrg6xgn76uda
« Previous Showing results 1 — 15 out of 959 results