A multi-neuro tagger using variable lengths of contexts

LuperFoy, Susann; Loehr, Dan; Duff, David G.; Miller, Keith J.; Reeder, Florence; Harper, Lisa; Ma, Qing; Isahara, Hitoshi

doi:10.3115/980691.980701

Cited by 9 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous systems proposed by Ma, et al, the inputs for the words on the left are constructed using the already tagged results (see details in [5] …”

Section: Pos Tagging Problemsmentioning

confidence: 99%

“…[5,6], the pattern is weighted using information gain (denoted by IG) which can be obtained from the training data using information theory.…”

Section: Pos Tagging Problemsmentioning

confidence: 99%

“…To construct a practical tagger that uses as few training data as possible, POS tagging systems that consists of multiple neural networks [5] or a single neural network with elastic input [6] were proposed by Ma, et al Both of these systems were more than 94% accurate (counting only the ambiguous words in POSs) when tagging untrained data from a small Thai corpus with 22,311 ambiguous words available for training.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Part of speech tagging with min‐max modular neural networks

Ma¹,

Isahara³

et al. 2002

Systems & Computers in Japan

Self Cite

View full text Add to dashboard Cite

Part of speech tagging systems using neural networks have been proposed by Ma, et al. They can tag the untrained data at a practical level of accuracy by training a small Thai corpus with ten thousand order words. The multilayer perceptron (MLP) type of neural networks used, however, was found to converge slowly and took a very long time to train even the above mentioned small amount of training data. This paper presents an alternative method for solving the POS tagging problems with the min-max modular neural network proposed by Lu and Ito. By using this modular neural network, the part of speech tagging problems can be broken down into a number of independent smaller and simpler subproblems, and all of the subproblems can be learned by small network modules in parallel.

show abstract

“…In previous systems proposed by Ma, et al, the inputs for the words on the left are constructed using the already tagged results (see details in [5] …”

Section: Pos Tagging Problemsmentioning

confidence: 99%

“…[5,6], the pattern is weighted using information gain (denoted by IG) which can be obtained from the training data using information theory.…”

Section: Pos Tagging Problemsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Part of speech tagging with min‐max modular neural networks

Ma¹,

Isahara³

et al. 2002

Systems & Computers in Japan

Self Cite

View full text Add to dashboard Cite

show abstract

Untitled

Ichikawa

et al. 2003

Applied Intelligence

View full text Add to dashboard Cite

Classifiers combination to arabic morphosyntactic disambiguation

Albared

Omar

Aziz

2009

2009 International Conference on Electrical Engineering and Informatics

View full text Add to dashboard Cite

Parts of speech tagging forms the important preprocessing step in many of the natural language processing applications like text summarization, question answering and information retrieval system. MorphoSyntactic disambiguation (part of speech tagging) is the process of classifying every word in a given context to its appropriate part of speech. In this paper, we first review all the supervised machine learning approaches that have been used in the part of speech tagging. Then we review all the Arabic works to compare and to confirm our need to develop an accurate and efficient Arabic MorphoSyntactic Disambiguation system. Finally we propose a classifiers combination experimental framework for Arabic part of speech tagger in which three diverse probabilistic classifiers (Hidden Markov, Maximum Entropy and Transformation Based Learning) are combined using many different combination strategies to exploit their advantages Keywords-natural language processing, MorphoSyntactic disambiguation, machine learning.

show abstract

A multi-neuro tagger using variable lengths of contexts

Cited by 9 publications

References 6 publications

Part of speech tagging with min‐max modular neural networks

Part of speech tagging with min‐max modular neural networks

Untitled

Classifiers combination to arabic morphosyntactic disambiguation

Contact Info

Product

Resources

About