Sciweavers

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

9

ACL
2001

favoriteEmaildiscussreport

151views Computational Linguistics» more ACL 2001»

Improvement of a Whole Sentence Maximum Entropy Language Model Using Grammatical Features

13 years 5 months ago

Improvement of a Whole Sentence Maximum Entropy Language Model Using Grammatical Features

Download acl.ldc.upenn.edu

In this paper, we propose adding long-term grammatical information in a Whole Sentence Maximun Entropy Language Model (WSME) in order to improve the performance of the model. The grammatical information was added to the WSME model as features and were obtained from a Stochastic Context-Free grammar. Finally, experiments using a part of the Penn Treebank corpus were carried out and significant improvements were acheived.

Fredy A. Amaya, José-Miguel Benedí

Real-time Traffic

ACL 2001 | ACL 2007 | Entropy Language Model | Grammatical Information | Long-term Grammatical Information |

claim paper

Related Content

» Trimming CFG Parse Trees for Sentence Compression Using Machine Learning Approaches

» Unsupervised Discriminative Language Model Training for Machine Translation using Simulate...

» Using a Smoothing Maximum Entropy Model for Chinese Nominal Entity Tagging

» Discriminative Approach to PredicateArgument Structure Analysis with ZeroAnaphora Resoluti...

» Maximum Entropy Based Phrase Reordering for Hierarchical PhraseBased Translation

» A Direct SyntaxDriven Reordering Model for PhraseBased Machine Translation

» A Chunking Strategy Towards Unknown Word Detection in Chinese Word Segmentation

» Semantic and Syntactic Features for Dutch Coreference Resolution

» Trainable Methods for Surface Natural Language Generation

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2001
Where	ACL
Authors	Fredy A. Amaya, José-Miguel Benedí

Comments (0)