Neural Network Approach to Thai Part Of Speech Tagging
نویسندگان
چکیده
Thai part of speech (POS) tagging is a challenged problem in natural language processing. Many techniques including artificial neural network techniques are suggested for POS tagging. Research works in Thai POS tagging so far only focused on assigning word types, but not word features. This paper proposed a technique using multilayer perception for tagging word features in Thai sentences. The features indicate roles of the word in the sentence. This POS tagging is called Role-POS tagging. The experimental results show that the neural network technique is an appropriated tool for word feature tagging in Thai language.
منابع مشابه
Part-Of-Speech Tagging of Thai Corpus with the Logically Combined Neural Networks
This paper presents a new part-of-speech (POS) tagger for the Thai corpus that is able to use the di erent lengths of contexts as needed for tagging. The new tagger is constructed by the logically combined neural networks, all of which are idividual taggers with xed but di erent lengths of contexts in inputs. Computer experiments show that the tagger has a success rate of over 87% for tagging o...
متن کاملPart of Speech Tagging in Thai Language Using Support Vector Machine
The elastic-input neuro tagger and hybrid tagger, combined with a neural network and Brill's error-driven learning, have already been proposed for the purpose of constructing a practical tagger using as little training data as possible. When a small Thai corpus is used for training, these taggers have tagging accuracies of 94.4% and 95.5% (accounting only for the ambiguous words in terms of the...
متن کاملبرچسبگذاری ادات سخن زبان فارسی با استفاده از مدل شبکۀ فازی
Part of speech tagging (POS tagging) is an ongoing research in natural language processing (NLP) applications. The process of classifying words into their parts of speech and labeling them accordingly is known as part-of-speech tagging, POS-tagging, or simply tagging. Parts of speech are also known as word classes or lexical categories. The purpose of POS tagging is determining the grammatical ...
متن کاملMassively Parallel Part of Speech Tagging Using Min-Max Modular Neural Networks
This paper presents a massively parallel tagging method for automatically assigning the correct part of speech (POS) tag to each ambiguous word in a sentence in the context of the sentence. This method is based on the min-max modular neural network, an e cient modular neural network model for solving large-scale pattern recognition problems. The method has two attractive features. One is that i...
متن کاملElastic neural networks for part of speech tagging
This paper presents a part of speech (POS) neuro tagger which consists of a 3-layer perceptron with elastic input. Computer experiments show that the neuro tagger has an accuracy of 94.4% for tagging ambiguous words when a small Thai corpus with 22,311 ambiguous words is used for training. A series of comparative experiments further show that the neuro tagger is de nitely far superior to the st...
متن کامل