Filters








11,388 Hits in 6.0 sec

Estimating Grammar Parameters Using Bounded Memory [chapter]

Tim Oates, Brent Heeringa
2002 Lecture Notes in Computer Science  
The memory used by HOLA is bounded by the size of the grammar, not by the amount of training data.  ...  Estimating the parameters of stochastic context-free grammars (SCFGs) from data is an important, well-studied problem.  ...  Experiments This section shows empirically that HOLA learns good parameter estimates using bounded memory.  ... 
doi:10.1007/3-540-45790-9_15 fatcat:x4nyvipd7naeha57wntemxrezq

Language learning: how much evidence does a child need in order to learn to speak grammatically?

K PAGE
2004 Bulletin of Mathematical Biology  
We reformulate this algorithm in the context of Chomsky's 'principles and parameters' and show that it is possible to bound the amount of evidence required to almost certainly speak almost grammatically  ...  Thus early language development involves refinement of the grammar hypothesis until a target grammar is learnt.  ...  Secondly, we consider what happens when the learner has no memory for sentences and can only use a given sentence to compare the two grammars that she/he is currently considering.  ... 
doi:10.1016/j.bulm.2003.09.007 pmid:15210311 fatcat:5o5ii526wbbejldcxnpmysm42i

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  
Inference with Multinomial Tests p. 149 Learning Languages with Help p. 161 Incremental Learning of Context Free Grammars p. 174 Estimating Grammar Parameters Using Bounded Memory p. 185 Stochastic  ...  Used with permission. p. 28 Beyond EDSM p. 37 Consistent Identification in the Limit of Rigid Grammars from Strings Is NP-hard p. 49 Some Classes of Regular Languages Identifiable in the Limit  ... 
doi:10.1007/3-540-45790-9_6 fatcat:nmlknwqoyfbybhb6rpomqrn7qy

Page 1297 of Mathematical Reviews Vol. 29, Issue 6 [page]

1965 Mathematical Reviews  
Call G a linear bounded grammar (“grammar with linear memory” in the author’s terminology) if there exists a natural number k such that for any word W e L(@), obtained, say, by a derivation S= W,>W,—-  ...  V. 6967 Grammars with linear memory. (Russian) Algebra i Logika Sem. 2 (1963), no. 5, 43-55.  ... 

Parsing the wall street journal using a Lexical-Functional Grammar and discriminative estimation techniques

Stefan Riezler, Tracy H. King, Ronald M. Kaplan, Richard Crouch, John T. Maxwell, Mark Johnson
2001 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02  
The treebank annotations are used to provide partially labeled data for discriminative statistical estimation using exponential models.  ...  The model combines full and partial parsing techniques to reach full grammar coverage on unseen data.  ...  A final capability of XLE that increases coverage of the standard-plus-fragment grammar is a SKIMMING technique. Skimming is used to avoid timeouts and memory problems.  ... 
doi:10.3115/1073083.1073129 dblp:conf/acl/RiezlerKKCMJ02 fatcat:axjfhuyzczf2lohdv3gtgbyqjm

Structural Selectivity Estimation for XML Documents

Damien K. Fisher, Sebastian Maneth
2007 2007 IEEE 23rd International Conference on Data Engineering  
A new synopsis for XML documents is introduced which can be effectively used to estimate the selectivity of complex path queries.  ...  Virtually all database systems rely on the use of selectivity estimates to choose amongst the many possible execution plans for a particular query.  ...  Acknowledgment The authors gratefully thank Neoklis Polyzotis for providing us with an implementation of his TreeSketch estimation framework.  ... 
doi:10.1109/icde.2007.367908 dblp:conf/icde/FisherM07 fatcat:3j6vt7se5vebddf3qtd2mjuspa

Unsupervised Grammar Induction with Depth-bounded PCFG [article]

Lifeng Jin, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz
2018 arXiv   pre-print
This work extends this depth-bounding approach to probabilistic context-free grammar induction (DB-PCFG), which has a smaller parameter space than hierarchical sequence models, and therefore more fully  ...  There has been recent interest in applying cognitively or empirically motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson,  ...  This depth-bounded grammar is then used to derive left-corner expectations (anticipated counts of categories appearing as left descendants of other categories), and ultimately the parameters of the depth-bounded  ... 
arXiv:1802.08545v2 fatcat:ncpudi2uljcqva3h4ivpidijzm

Depth-Bounded Statistical PCFG Induction as a Model of Human Grammar Acquisition

Lifeng Jin, Lane Schwartz, Finale Doshi-Velez, Timothy A. Miller, William Schuler
2021 Computational Linguistics  
An implementation of these memory bounds as limits on center embedding in a depth-specific transform of a recursive grammar yields a significant improvement over an equivalent but unbounded baseline, suggesting  ...  memory capacity, where the shallow grammars are constrained images of the Submission Volume 47, Number 1 recursive grammars.  ...  Using context-free grammars (CFGs) to define these structures with labels, previous attempts at either CFG parameter estimation (Carroll and Charniak 1992; Pereira and Schabes 1992; Johnson, Griffiths  ... 
doi:10.1162/coli_a_00399 dblp:journals/coling/JinSDMS21 fatcat:h7plwbgjxjczbe3ykqmixikuya

Graphical EM for on-line learning of grammatical probabilities in radar Electronic Support

Guillaume Latombe, Eric Granger, Fred A. Dilkes
2012 Applied Soft Computing  
The impact on performance of factors like the size of new data blocks, and the level of ambiguity of grammars has been observed.  ...  As expected, on-line learning significantly reduces the overall time and memory complexities associated with updating probabilities with new data in an operational environment.  ...  They used an English phrase grammar, a palindrome-generating grammar, and a simple ambiguous grammar.  ... 
doi:10.1016/j.asoc.2012.02.022 fatcat:ftyrcx37wnexlaoghuutgninae

Design and Deployment of Photo2Building: A Cloud-based Procedural Modeling Tool as a Service

Manush Bhatt, Rajesh Kalyanam, Gen Nishida, Liu He, Christopher May, Dev Niyogi, Daniel Aliaga
2020 Practice and Experience in Advanced Research Computing  
This provides for an extremely scalable and possibly widespread tool for creating building models for use in urban design and planning applications.  ...  To determine the building mass style and camera parameters, first a recognition CNN is used. Then, our approach uses a per-style parameter estimation CNN to estimate the actual grammar parameters.  ...  As with the building-mass grammar styles, each facade grammar style contains multiple parameters such as floor height, window/door size, and appearance, which are estimated using a parameter estimation  ... 
doi:10.1145/3311790.3396670 dblp:conf/xsede/BhattKNHMNA20 fatcat:artwxkujrvbtdankatup7mkfey

Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction

Lifeng Jin, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
constituency-based grammar induction models.  ...  There have been several recent attempts to improve the accuracy of grammar induction systems by bounding the recursive complexity of the induction model (Ponvert et al., 2011; Noji and Johnson, 2016; Shain  ...  Using context-free grammars (CFGs) to define these structures, previous attempts at either CFG parameter estimation (Carroll and Charniak, 1992; Schabes and Pereira, 1992; Johnson et al., 2007b) or directly  ... 
doi:10.18653/v1/d18-1292 dblp:conf/emnlp/JinDMSS18 fatcat:kxytcssbjjarto4ieza6wdar3e

Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction [article]

Lifeng Jin, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz
2018 arXiv   pre-print
constituency-based grammar induction models.  ...  There have been several recent attempts to improve the accuracy of grammar induction systems by bounding the recursive complexity of the induction model (Ponvert et al., 2011; Noji and Johnson, 2016; Shain  ...  Using context-free grammars (CFGs) to define these structures, previous attempts at either CFG parameter estimation (Carroll and Charniak, 1992; Schabes and Pereira, 1992; Johnson et al., 2007b) or directly  ... 
arXiv:1809.03112v1 fatcat:nemr2b2qyjgxtpmeuit4caap6i

Procedural Modeling of a Building from a Single Image

Gen Nishida, Adrien Bousseau, Daniel G. Aliaga
2018 Computer graphics forum (Print)  
This methodology consists in simplifying the input image to match the visual appearance of synthetic training data, and in using optimization to refine the parameters estimated by CNNs.  ...  In the first stage, our method jointly estimates camera parameters and building mass shape.  ...  Acknowledgements We would like to thank the authors of DeepFacade [LZZH17] for helping us generate façade parsing results, and the anonymous reviewers for their constructive suggestions.  ... 
doi:10.1111/cgf.13372 fatcat:vnisacbqujasbowvqh5qzfdya4

An Algorithm for Universal Lossless Compression With Side Information

H. Cai, S.R. Kulkarni, S. Verdu
2006 IEEE Transactions on Information Theory  
The MPM code transforms the data sequence into a grammar, which is then compressed by the zero-order adaptive arithmetic code. The MPM grammar with parameter is as follows.  ...  Following the technique in [14] , Theorem 1 provides an upper bound on the compression ratio using the basic CTW method with maximal memory length .  ... 
doi:10.1109/tit.2006.880020 fatcat:lfhggbk2pzhzdirtzugbt2slce

Interactive sketching of urban procedural models

Gen Nishida, Ignacio Garcia-Dorado, Daniel G. Aliaga, Bedrich Benes, Adrien Bousseau
2016 ACM Transactions on Graphics  
We use nonphotorealistic rendering to generate artificial data for training convolutional neural networks capable of quickly recognizing the procedural rule intended by a sketch and estimating its parameters  ...  Our system uses a collection of simple procedural grammars, called snippets, as building blocks to turn sketches into realistic 3D models.  ...  recognize grammar snippets and estimate their parameters in less than a second.  ... 
doi:10.1145/2897824.2925951 fatcat:3bgo7szfozfj7kic65rab27vqm
« Previous Showing results 1 — 15 out of 11,388 results