Data-driven parsing using probabilistic linear context-free rewriting systems
L Kallmeyer, W Maier - Computational Linguistics, 2013 - direct.mit.edu
This paper presents the first efficient implementation of a weighted deductive CYK parser for
Probabilistic Linear Context-Free Rewriting Systems (PLCFRSs). LCFRS, an extension of …
Probabilistic Linear Context-Free Rewriting Systems (PLCFRSs). LCFRS, an extension of …
Data-oriented parsing with discontinuous constituents and function tags
Statistical parsers are e ective but are typically limited to producing projective dependencies
or constituents. On the other hand, linguisti-cally rich parsers recognize non-local relations …
or constituents. On the other hand, linguisti-cally rich parsers recognize non-local relations …
[PDF][PDF] PLCFRS parsing revisited: Restricting the fan-out to two
W Maier, M Kaeshammer… - Proceedings of the 11th …, 2012 - aclanthology.org
Abstract Linear Context-Free Rewriting System (LCFRS) is an extension of Context-Free
Grammar (CFG) in which a non-terminal can dominate more than a single continuous span …
Grammar (CFG) in which a non-terminal can dominate more than a single continuous span …
Discontinuous parsing with an efficient and accurate DOP model
A Van Cranenburgh, R Bod - Proceedings of IWPT, 2013 - research.rug.nl
We present a discontinuous variant of treesubstitution grammar (tsg) based on Linear
Context-Free Rewriting Systems. We use this formalism to instantiate a Data-Oriented …
Context-Free Rewriting Systems. We use this formalism to instantiate a Data-Oriented …
Efficient parsing with linear context-free rewriting systems
A Van Cranenburgh - Proceedings of EACL, 2012 - research.rug.nl
Previous work on treebank parsing with discontinuous constituents using Linear Context-
Free Rewriting systems (LCFRS) has been limited to sentences of up to 30 words, for …
Free Rewriting systems (LCFRS) has been limited to sentences of up to 30 words, for …
[PDF][PDF] Learning from errors: Using vector-based compositional semantics for parse reranking
In this paper, we address the problem of how to use semantics to improve syntactic parsing,
by using a hybrid reranking method: a k-best list generated by a symbolic parser is reranked …
by using a hybrid reranking method: a k-best list generated by a symbolic parser is reranked …
Transition-based dependency parsing as latent-variable constituent parsing
MJ Nederhof - Proceedings of the SIGFSM …, 2016 - research-repository.st-andrews.ac …
We provide a theoretical argument that a common form of projective transition-based
dependency parsing is less powerful than constituent parsing using latent variables. The …
dependency parsing is less powerful than constituent parsing using latent variables. The …
[PDF][PDF] Two characterisation results of multiple context-free grammars and their application to parsing
T Denkinger - 2019 - researchgate.net
Two characterisation results of multiple context-free grammars and their application to parsing
Page 1 Two characterisation results of multiple context-free grammars and their application to …
Page 1 Two characterisation results of multiple context-free grammars and their application to …
[PDF][PDF] Induction, Training, and Parsing Strategies beyond Context-free Grammars
K Gebhardt - 2020 - core.ac.uk
A distinguishing feature of humankind is the capacity to use symbolic language for
communication and representation of information. Computers, which are meant to process …
communication and representation of information. Computers, which are meant to process …
[图书][B] Learning Vector Representations for Sentences-The Recursive Deep Learning Approach
P Lê - 2016 - eprints.illc.uva.nl
Natural language processing (NLP) systems, until recently, relied heavily on sophisticated
representations and carefully designed feature sets. Now with the rise of deep learning, for …
representations and carefully designed feature sets. Now with the rise of deep learning, for …