In text representation, topic keywords should be given greater weights.

Feature extraction and text representation are keys to the performance of text classification.

特征提取及文本表示是影响文本分类结果的关键。

互联网摘选

Text Representation Based on Sentence and Chinese Text Categorization

基于句子的文本表示及中文文本分类研究

互联网摘选

Comparison of Two Text Representation Methods

自动文本分类中两种文本表示方式的比较

互联网摘选

Comparative study on text representation schemes in Chinese text classification

中文文本分类中的文本表示因素比较

互联网摘选

We propose two text representation methods using domain knowledge.

我们提出将领域知识应用于文本特征表示的两种方法。第一种表示：用领域知识库中的领域特征概念作为文本的特征；

互联网摘选

The Study of Chinese Text Representation and Classification Based on Multi-Instance Learning

基于多示例学习的中文文本表示及分类研究

互联网摘选

Study on Feature Extraction and Text Representation Technology in Topic Tracking

面向话题追踪的特征选取与文本表示技术的研究

互联网摘选

This paper expounds the importance of translator's coherence thought in the process of translation, including understanding of the original text, reconstructing of the faithful and smooth translated text, and proofreading of the translated text in the whole.

文章从对原文意义精确的把握，重构忠实而又通顺的译文，和最后从整体上对译文的校对，这翻译的三个基本步骤来阐述译者具备语篇连贯思维的重要性。

互联网摘选

This chapter focuses on the language data collection, recording to writing, text processing, segmentation proofreading.

第二章介绍语料库建设情况，包括语料采集、录音转写、文本处理、分词校对四个方面。

互联网摘选

Chinese text automatic proofreading, a part of application foundation research of natural language processing, taking the chance of the development of e-journal, gradually gets more and more enough attention, also becomes an urgency task.

而中文文本自动校对，属于自然语言处理的应用基础研究范畴，以出版业的电子化迅猛发展为契机，也越来越受到足够的重视，并成为一项亟待解决的紧迫课题。

互联网摘选

The research on Mongolian syntax and phrase is urgently in need for Mongolian corpus automatic segmentation, tagging, machine translation, text automatic proofreading and optical character recognition.

现阶段的蒙古文语料库加工、文本校对、文字识别及机器翻译等工程迫切需要面向信息处理的蒙古语句法、短语研究。

互联网摘选

The composition and critical techique of Chinese text automatic proofreading system are given.

给出了中文文本自动校对系统的组成及关键技术。

互联网摘选

Chinese Text Automatic Proofreading Research and System Composition

中文文本自动校对技术研究及系统组成

互联网摘选

This paper introduces the basic patterns of language information processing and the classifying system of modern Chinese terms that the grammatical information dictionary follows, illustrating the roles of grammar knowledge and grammar study in language information processing from Chinese input and text proofreading.

首先介绍了语言信息处理的基本模型和语法信息词典所遵循的现代汉语词语分类体系，然后从中文输入和文本校对两个方面阐述语法知识与语法研究在语言信息处理中的重要作用。

互联网摘选

Traditional Uyghur text proofreading techniques are mainly based on huge corpus and word frequency-based statistical methods, there are many limitations.

传统的维吾尔语文本校对技术都是以庞大的词库、词的出现频率统计方法为主的，有很多的局限性。

互联网摘选

This paper gives an overview of the main idea and algorithms of Chinese text proofreading, the system structure and applications are discussed too.

本文简要介绍了中文自动校对的主要原理和基本算法，讨论了校对软件系统现有工作方式及校对流程。

互联网摘选

The Structuring Method of Correcting Knowledge Sets and the Producing Algorithm of Correcting Suggestion in the Chinese Text Proofreading System

中文校对系统中纠错知识库的构造及纠错建议的产生算法

互联网摘选

The Research of Multi-Feature Chinese Text Proofreading Algorithms

多特征的中文文本校对算法的研究

互联网摘选

The Research of Chinese Text Proofreading System Model Based on HNC

基于HNC的中文文本校对系统模型的研究

互联网摘选

CI-NLU Based Text Processing After Speech Recognition

基于全信息自然语言理解的语音识别后文本处理

互联网摘选