Dictionary learning method and device therefore, input method and user terminal using the method

Abstract

The invention discloses a dictionary learning method, which includes the following steps: a dictionary and a statistical language model are learned in language material which is not marked; the dictionary, the statistical language model and auxiliary word coded information are conformed as a small size dictionary. Furthermore, the invention also discloses an input method used in a user terminal device and the user terminal device, wherein, the terminal device is loaded the dictionary with the part of speech information and the part of the double-unit model. Therefore, a sentence prediction and a word prediction are given by the user terminal device, meanwhile, the dictionary is searched by using the Patricia tree index in the dictionary index, and the input speed is increased.

Description

technical field [0001] The present invention relates to a natural language processing, and more specifically, to a dictionary learning method and a device using the dictionary learning method, an input method and a user terminal device using the input method. Background technique [0002] With the widespread use of computers, PDAs, and mobile phones in China, it can be seen that an important feature of these devices is the ability to enable users to input Chinese. In China's current mobile terminal market, almost every mobile phone provides an input method using a numeric keypad. Currently the most widely used input methods are T9 and iTap. With this input method, the user can use the ten-key numeric keypad to input pinyin or strokes of Chinese characters. attached Figures 8A-8B An example keyboard for pinyin and stroke input is shown. The input method gives predictions of Chinese characters according to the sequence of keys tapped by the user. When the user inputs the ...

AI Technical Summary

Problems solved by technology

However, this SLM uses a predetermined dictionary and stores a large number of word bigrams and word triplets in the dictionary, and the size of the dictionary will inevitably be too large to be installed on a mobile terminal.

In addition, the prediction speed on the mobile terminal platform is also very slow

[0008] Another disadvantage is that most input methods do not have dictionaries or only include predefined dictionaries

Therefore, it is not possible to continuously input multiple important words and phrases frequently used in the language, such as "this afternoon"

Images