Sciweavers

    8 search results - page 1 / 2
    » Loss Minimization in Parse Reranking
    Sort
    View
    EMNLP
    2006
    130views Natural Language Processing» more  EMNLP 2006»
    Loss Minimization in Parse Reranking
    13 years 6 months ago
    Loss Minimization in Parse Reranking
    Download  homepages.inf.ed.ac.uk
    We propose a general method for reranker construction which targets choosing the candidate with the least expected loss, rather than the most probable candidate. Different approac...
    Ivan Titov, James Henderson
    claim paper
    Read More »
    ICML
    2007
    IEEE
    119views Machine Learning» more  ICML 2007»
    Scalable training of L1-regularized log-linear models
    14 years 5 months ago
    Scalable training of L1-regularized log-linear models
    Download  www.machinelearning.org
    The l-bfgs limited-memory quasi-Newton method is the algorithm of choice for optimizing the parameters of large-scale log-linear models with L2 regularization, but it cannot be us...
    Galen Andrew, Jianfeng Gao
    claim paper
    Read More »
    NAACL
    2007
    136views Computational Linguistics» more  NAACL 2007»
    Improved Inference for Unlexicalized Parsing
    13 years 6 months ago
    Improved Inference for Unlexicalized Parsing
    Download  www.petrovi.de
    We present several improvements to unlexicalized parsing with hierarchically state-split PCFGs. First, we present a novel coarse-to-fine method in which a grammar’s own hierarc...
    Slav Petrov, Dan Klein
    claim paper
    Read More »
    AAAI
    2007
    123views Intelligent Agents» more  AAAI 2007»
    Learning and Inference for Hierarchically Split PCFGs
    13 years 7 months ago
    Learning and Inference for Hierarchically Split PCFGs
    Download  www.petrovi.de
    Treebank parsing can be seen as the search for an optimally refined grammar consistent with a coarse training treebank. We describe a method in which a minimal grammar is hierarc...
    Slav Petrov, Dan Klein
    claim paper
    Read More »
    NAACL
    2010
    152views Computational Linguistics» more  NAACL 2010»
    Ensemble Models for Dependency Parsing: Cheap and Good?
    13 years 2 months ago
    Ensemble Models for Dependency Parsing: Cheap and Good?
    Download  www-nlp.stanford.edu
    Previous work on dependency parsing used various kinds of combination models but a systematic analysis and comparison of these approaches is lacking. In this paper we implemented ...
    Mihai Surdeanu, Christopher D. Manning
    claim paper
    Read More »
    Explore & Download
    Proceedings Preprints Top 5 Ranked Papers Publications Books Software Tutorials Presentations Lectures Notes Datasets
    Productivity Tools
    International On-screen Keyboard Graphical Social Symbols OCR Text Recognition CSS3 Style Generator Web Page to PDF Web Page to Image PDF Split PDF Merge Latex Equation Editor Sci2ools
    Document Tools
    PDF to Text PDF to Postscript PDF to Thumbnails Excel to PDF Word to PDF Postscript to PDF PowerPoint to PDF Latex to Word Repair Corrupted PDF
    Image Tools
    JPG to PS JPG to PDF Extract Images from PDF Image Converter
    Sciweavers
    About Community Cookies Privacy Policy Terms of Use

    Copyright © Sciweavers LLC, 2009-2024, USA.