Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

ACL
2007

favoriteEmaildiscussreport

118views Computational Linguistics» more ACL 2007»

Grammar Approximation by Representative Sublanguage: A New Model for Language Learning

13 years 6 months ago

Grammar Approximation by Representative Sublanguage: A New Model for Language Learning

Download umiacs.umd.edu

We propose a new language learning model that learns a syntactic-semantic grammar from a small number of natural language strings annotated with their semantics, along with basic assumptions about natural language syntax. We show that the search space for grammar induction is a complete grammar lattice, which guarantees the uniqueness of the learned grammar.

Smaranda Muresan, Owen Rambow

Real-time Traffic

ACL 2007 | Complete Grammar Lattice | Computational Linguistics | Grammar | Natural Language |

claim paper

Related Content

» Meaning Helps Learning Syntax

» Multilingual Deep Lexical Acquisition for HPSGs via Supertagging

» Evolving Distributed Representations for Language with SelfOrganizing Maps

» Turbo Parsers Dependency Parsing by Approximate Variational Inference

» Almost All Learning Machines are Singular

» Bayesian Inductive Logic Programming

Post Info
More Details (n/a)

Added	29 Oct 2010
Updated	29 Oct 2010
Type	Conference
Year	2007
Where	ACL
Authors	Smaranda Muresan, Owen Rambow

Comments (0)