Filters








1,027 Hits in 4.6 sec

Best parse parsing with Earley's and Inside algorithms on probabilistic RTN

Young S. Han, Key-Sun Choi
1995 Natural Language Engineering  
The redundancy of Inside algorithm can be reduced by the topdown filtering using the chart produced by Earley algorithm, which is useful in training the probabilistic parameters of a grammar.  ...  Inside parsing is a best parse parsing method based on the Inside algorithm that is often used in estimating probabilistic parameters of stochastic context free grammars.  ...  Earley, Inside, and Efficient Inside parsing with test set III on network VII. Efficient Inside parsing saved 46% of the cost of Inside parsing.  ... 
doi:10.1017/s1351324900000127 fatcat:t5hiwhain5bazc5kyg3zzag6qa

Xml data dissemination using automata on top of structured overlay networks

Iris Miliaraki, Zoi Kaoudi, Manolis Koubarakis
2008 Proceeding of the 17th international conference on World Wide Web - WWW '08  
We present a novel approach for filtering XML documents using nondeterministic finite automata and distributed hash tables.  ...  The essence of our work is a distributed implementation of YFilter, a state-of-the-art automata-based XML filtering system on top of Chord.  ...  Since XML is widely used as the standard format for data exchange on the Web, a lot of research has focused on designing efficient and scalable XML filtering systems.  ... 
doi:10.1145/1367497.1367614 dblp:conf/www/MiliarakiKK08 fatcat:hzrdc353mnckrnbljodpv35laq

A Fast Unified Model for Parsing and Sentence Understanding

Samuel R. Bowman, Jon Gauthier, Abhinav Rastogi, Raghav Gupta, Christopher D. Manning, Christopher Potts
2016 Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences.  ...  We address these issues by introducing the Stack-augmented Parser-Interpreter Neural Network (SPINN), which combines parsing and interpretation within a single tree-sequence hybrid model by integrating  ...  Some of the Tesla K40s used for this research were donated by the NVIDIA Corporation.  ... 
doi:10.18653/v1/p16-1139 dblp:conf/acl/BowmanGRGMP16 fatcat:43j7ghruuzcmta3gvr664fzlh4

A Fast Unified Model for Parsing and Sentence Understanding [article]

Samuel R. Bowman, Jon Gauthier, Abhinav Rastogi, Raghav Gupta, Christopher D. Manning, Christopher Potts
2016 arXiv   pre-print
Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences.  ...  We address these issues by introducing the Stack-augmented Parser-Interpreter Neural Network (SPINN), which combines parsing and interpretation within a single tree-sequence hybrid model by integrating  ...  Some of the Tesla K40s used for this research were donated by the NVIDIA Corporation. We also thank Kelvin Guu, Noah Goodman, and many others in the Stanford NLP group for helpful comments.  ... 
arXiv:1603.06021v3 fatcat:oejlz7jolrhc5gg2yeljl23rcm

Recurrent Neural Network Grammars [article]

Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith
2016 arXiv   pre-print
We explain efficient inference procedures that allow application to both parsing and language modeling.  ...  We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure.  ...  Parser Transitions The parsing algorithm transforms a sequence of words x into a parse tree y using two data structures (a stack and an input buffer).  ... 
arXiv:1602.07776v4 fatcat:6lhz5ectzbhhfovqgepcc44opu

Efficient Earley Parsing with Regular Right-hand Sides

Trevor Jim, Yitzhak Mandelbaum
2010 Electronical Notes in Theoretical Computer Science  
We present a new variant of the Earley parsing algorithm capable of efficiently supporting context-free grammars with regular right hand-sides.  ...  Parsing transducers Our parsers are closely related to the augmented transition networks (ATNs) of Woods [13] .  ...  Finally, "ATN" is a version of the algorithm that uses a transducer that closely corresponds to Woods' augmented transition networks (see Section 3).  ... 
doi:10.1016/j.entcs.2010.08.037 fatcat:ciwrx27ribg6xaishvrfnakznm

Recurrent Neural Network Grammars

Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
We explain efficient inference procedures that allow application to both parsing and language modeling.  ...  We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure.  ...  Parser Transitions The parsing algorithm transforms a sequence of words x into a parse tree y using two data structures (a stack and an input buffer).  ... 
doi:10.18653/v1/n16-1024 dblp:conf/naacl/DyerKBS16 fatcat:v6c3wr3ssfa7hc47wyigk3wur4

Massively parallel XML twig filtering using dynamic programming on FPGAs

Roger Moussalli, Mariam Salloum, Walid Najjar, Vassilis J. Tsotras
2011 2011 IEEE 27th International Conference on Data Engineering  
XML Filtering The popularity of XML has triggered research efforts to build efficient XML filtering systems.  ...  The use of FPGAs in a distributed network system for traffic control information processing is demonstrated in [18] .  ... 
doi:10.1109/icde.2011.5767899 dblp:conf/icde/MoussalliSNT11 fatcat:5zzgcorgrreedaejhrnuz6qgxy

FoXtrot

Iris Miliaraki, Manolis Koubarakis
2012 ACM Transactions on the Web  
In this work, we design and implement FoXtrot, a system for filtering XML data that combines the strengths of automata for efficient filtering and distributed hash tables for building a fully distributed  ...  In this context, many XML filtering systems have been proposed to efficiently identify XML data that matches user interests expressed as queries in an XML query language like XPath.  ...  ACKNOWLEDGMENTS We would like to thank Mema Roussopoulos for useful comments and discussions.  ... 
doi:10.1145/2344416.2344419 fatcat:olpe4hk6uvgr7jz6gkqcfanvbq

Scalable XML query processing using parallel pushdown transducers

Peter Ogden, David Thomas, Peter Pietzuch
2013 Proceedings of the VLDB Endowment  
In online social networking, network monitoring and financial applications, there is a need to query high rate streams of XML data, but methods for executing individual XPath queries on streaming XML data  ...  Push transitions place the current state on the stack and pop transitions return the execution to the state being popped.  ...  pop transitions are represented by dashed arrows.  ... 
doi:10.14778/2556549.2556558 fatcat:tunpetdiwjhpxfhumlzuwcndna

Subsymbolic case-role analysis of sentences with embedded clauses

R Miikkulainen
1996 Cognitive Science  
A distributed neural network model called SPEC for processing sentences with recursive relative clauses is described.  ...  Elman (1991aElman ( , 1991b used the same network architecture to predict a context-free language with embedded clauses.  ...  These representations can then be used recursively as constituents in other input patterns.  ... 
doi:10.1016/s0364-0213(99)80002-0 fatcat:svo2i552qnddpc5eu5v63a4ux4

Subsymbolic Case-Role Analysis of Sentences with Embedded Clauses

Risto Miikkulainen
1996 Cognitive Science  
A distributed neural network model called SPEC for processing sentences with recursive relative clauses is described.  ...  Elman (1991aElman ( , 1991b used the same network architecture to predict a context-free language with embedded clauses.  ...  These representations can then be used recursively as constituents in other input patterns.  ... 
doi:10.1207/s15516709cog2001_2 fatcat:577j5fbbjvf2zi5ynnhais6cga

Learning an Executable Neural Semantic Parser [article]

Jianpeng Cheng and Siva Reddy and Vijay Saraswat and Mirella Lapata
2018 arXiv   pre-print
The generation process is modeled by structured recurrent neural networks, which provide a rich encoding of the sentential context and generation history for making predictions.  ...  The parser generates tree-structured logical forms with a transition-based approach which combines a generic tree-generation algorithm with domain-general operations defined by the logical language.  ...  A RED operation recursively pops the stack-LSTM states as well as corresponding tree tokens on the output stack.  ... 
arXiv:1711.05066v2 fatcat:afikadyvarevvjit7adoscsx7u

Grammar-aware Parallelization for Scalable XPath Querying

Lin Jiang, Zhijia Zhao
2017 Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP '17  
The benefits of path elimination go beyond reducing extra computation -it also enables the use of more efficient data structures, which further improves the efficiency.  ...  This paper presents GAP, a parallelization scheme that, for the first time, leverages the grammar of the input data to boost the parallelization efficiency.  ...  ., <a>) is read, the transducer first pushes the current state onto the stack, then transition to the next state based on the finite automaton. Pop transitions δ pop : Q × Σ × Γ → Q × ∆.  ... 
doi:10.1145/3018743.3018772 fatcat:3f4bbzzsebfkjmfmo644kczktu

Learning an Executable Neural Semantic Parser

Jianpeng Cheng, Siva Reddy, Vijay Saraswat, Mirella Lapata
2018 Computational Linguistics  
The generation process is modeled by structured recurrent neural networks, which provide a rich encoding of the sentential context and generation history for making predictions.  ...  The parser generates tree-structured logical forms with a transition-based approach which combines a generic tree-generation algorithm with domain-general grammar defined by the logical language.  ...  with transition-based neural networks.  ... 
doi:10.1162/coli_a_00342 fatcat:smuzyli3hvfd3knkzgbb64ppf4
« Previous Showing results 1 — 15 out of 1,027 results