Discriminative Training for Log-Linear Based SMT

2014 ◽  
Vol 13 (4) ◽  
pp. 1-25
Author(s):  
Lemao Liu ◽  
Tiejun Zhao ◽  
Taro Watanabe ◽  
Hailong Cao ◽  
Conghui Zhu
Keyword(s):  
Discriminative Training ◽  
Log Linear

scholarly journals Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models

2007 ◽  
Vol 33 (4) ◽  
pp. 493-552 ◽  
Author(s):  
Stephen Clark ◽  
James R. Curran
Keyword(s):  
Linear Models ◽  
Parallel Implementation ◽  
Discriminative Training ◽  
Training Data ◽  
Highly Efficient ◽  
Independent Events ◽  
Cluster Dynamic ◽  
Statistical Parsing ◽  
Parsing Algorithm ◽  
Log Linear

This article describes a number of log-linear parsing models for an automatically extracted lexicalized grammar. The models are “full” parsing models in the sense that probabilities are defined for complete parses, rather than for independent events derived by decomposing the parse tree. Discriminative training is used to estimate the models, which requires incorrect parses for each sentence in the training data as well as the correct parse. The lexicalized grammar formalism used is Combinatory Categorial Grammar (CCG), and the grammar is automatically extracted from CCGbank, a CCG version of the Penn Treebank. The combination of discriminative training and an automatically extracted grammar leads to a significant memory requirement (up to 25 GB), which is satisfied using a parallel implementation of the BFGS optimization algorithm running on a Beowulf cluster. Dynamic programming over a packed chart, in combination with the parallel implementation, allows us to solve one of the largest-scale estimation problems in the statistical parsing literature in under three hours. A key component of the parsing system, for both training and testing, is a Maximum Entropy supertagger which assigns CCG lexical categories to words in a sentence. The supertagger makes the discriminative training feasible, and also leads to a highly efficient parser. Surprisingly, given CCG's “spurious ambiguity,” the parsing speeds are significantly higher than those reported for comparable parsers in the literature. We also extend the existing parsing techniques for CCG by developing a new model and efficient parsing algorithm which exploits all derivations, including CCG's nonstandard derivations. This model and parsing algorithm, when combined with normal-form constraints, give state-of-the-art accuracy for the recovery of predicate-argument dependencies from CCGbank. The parser is also evaluated on DepBank and compared against the RASP parser, outperforming RASP overall and on the majority of relation types. The evaluation on DepBank raises a number of issues regarding parser evaluation. This article provides a comprehensive blueprint for building a wide-coverage CCG parser. We demonstrate that both accurate and highly efficient parsing is possible with CCG.

When and why are log-linear models self-normalizing?

2015 ◽  
Author(s):  
Jacob Andreas ◽  
Dan Klein
Keyword(s):  
Linear Models ◽  
Log Linear

Impact of Training and Development Programmes on the Productivity of Employees in the Banks

2016 ◽  
Vol 5 (1) ◽  
Author(s):  
Jaspreet Kaur
Keyword(s):  
Regression Analysis ◽  
Banking Sector ◽  
Human Resources Management ◽  
Training And Development ◽  
Linear Forms ◽  
Knowledge And Skills ◽  
Resources Management ◽  
Level Of Satisfaction ◽  
Log Linear ◽  
The Impact

Manpower training and development is an important aspect of human resources management which must be embarked upon either proactively or reactively to meet any change brought about in the course of time. Training is a continuous and perennial activity. It provides employees with the knowledge and skills to perform more effectively. The study examines the opinions of trainees regarding the impact of training and development programmes on the productivity of employees in the selected banks. To evaluate the impact of training and development programmes on productivity of banking sector, multiple regression analysis was employed in both log as well as log-linear forms. Also the impact of three sets of training i.e. objectives, methods and basics on level of satisfaction of respondents with the training was also examined through employing the regression analysis in the similar manner.

Sign in / Sign up

Export Citation Format

Share Document