Part of speech tagging with min-max modular neural networks

نویسندگان

  • Qing Ma
  • Bao-Liang Lu
  • Hitoshi Isahara
  • Michinori Ichikawa
چکیده

A parts of speech (POS) tagging system using neural networks has been developed by Ma and colleagues. This system can tag unlearned data with a much higher accuracy than that of the Hidden Markov Model (HMM), which is the most popular method of POS tagging. It does so by learning a small Thai corpus on the order of 10,000 words that are ambiguous as to their POSs. However, the threelayer perceptron used in the system has slow convergence and low learning accuracy even on such a small amount of data. It is therefore difficult to improve accuracy by incrementing the epoch of learning or by increasing the amount of learning data. To solve this problem, the tagging system of this paper makes use of the min-max modular (M) neural network of Lu and colleagues. This new system learns faster and has a higher learning accuracy compared with the old one, by decomposing large, complicated POS tagging problems into many smaller, easier problems. Learning accuracy can be improved by using the same learning data and larger data sets can be learned, which results in a much higher tagging accuracy. © 2002 Wiley Periodicals, Inc. Syst Comp Jpn, 33(7): 30–39, 2002; Published online in Wiley InterScience (www.interscience. wiley.com). DOI 10.1002/scj.1139

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Massively 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 کامل

معرفی شبکه های عصبی پیمانه ای عمیق با ساختار فضایی-زمانی دوگانه جهت بهبود بازشناسی گفتار پیوسته فارسی

In this article, growable deep modular neural networks for continuous speech recognition are introduced. These networks can be grown to implement the spatio-temporal information of the frame sequences at their input layer as well as their labels at the output layer at the same time. The trained neural network with such double spatio-temporal association structure can learn the phonetic sequence...

متن کامل

Part-Of-Speech Tagging With Neural Networks

Text corpora which are tagged with part-of-speech information are useful in many areas of linguistic research. In this paper, a new part-of-speech tagging method hased on neural networks (Net-Tagger) is presented and its performance is compared to that of a llMM-tagger (Cutting et al., 1992) and a trigrambased tagger (Kempe, 1993). It is shown that the Net-Tagger performs as well as the trigram...

متن کامل

Part of Speech Tagging with Mixed Approaches of Neural Networks and Transformation Rules

For the purpose of constructing a practical part of speech tagger that uses as few training data as possible, an approach using neural networks, which uses di erent lengths of contexts based on longest context priority and takes into account the maximization of information amount, have been proposed so far. To further improve the tagging performance, this paper proposes an integrated approach o...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Systems and Computers in Japan

دوره 33  شماره 

صفحات  -

تاریخ انتشار 2002