笔记-2002-Combining Classifiers for Chinese Word Segmentation
2012-11-06 17:46
537 查看
Combining Classifiers for Chinese Word Segmentation
作者:Nianwen Xue,Susan P. Converse
单位:Institute for Research in Cognitive Science ;University of Pennsylvania
出处:Proceeding SIGHAN '02 Proceedings of the first SIGHAN workshop on Chinese language processing - Volume 18 Association for Computational Linguistics Stroudsburg, PA, USA ©2002
主要内容:用最大熵解决中文分词问题,抛砖引玉
引言,Introduction
模型,
1为什么用tag解决,怎么tag
2 ME模型
3 ME有标记偏置问题,Transformation-Based Learning去解决
实验
3个实验的介绍
评价及结果分析
讨论
使用最大熵工具注意几点,
1 回车换行只有10 没有13
2 测试语料不能有空行,可以对结果再行处理
3 测试语料如果第一行是测试答案,则输出一个“标记”准确率,并不是P、R、F1
4 迭代次数可以显示对训练语料的拟合程度,Xue的这篇论文拟合程度至少是0.9755
作者:Nianwen Xue,Susan P. Converse
单位:Institute for Research in Cognitive Science ;University of Pennsylvania
出处:Proceeding SIGHAN '02 Proceedings of the first SIGHAN workshop on Chinese language processing - Volume 18 Association for Computational Linguistics Stroudsburg, PA, USA ©2002
主要内容:用最大熵解决中文分词问题,抛砖引玉
引言,Introduction
模型,
1为什么用tag解决,怎么tag
2 ME模型
3 ME有标记偏置问题,Transformation-Based Learning去解决
实验
3个实验的介绍
评价及结果分析
讨论
使用最大熵工具注意几点,
1 回车换行只有10 没有13
2 测试语料不能有空行,可以对结果再行处理
3 测试语料如果第一行是测试答案,则输出一个“标记”准确率,并不是P、R、F1
4 迭代次数可以显示对训练语料的拟合程度,Xue的这篇论文拟合程度至少是0.9755
相关文章推荐
- 笔记-2012-Unsupervized Word Segmentation the case for Mandarin Chinese
- 笔记-2006-Subword-based Tagging by Conditional Random Fields for Chinese Word Segmentation
- 笔记-2003-Chinese Word Segmentation as LMR Tagging
- 笔记-2003-Chinese Word Segmentation as Character Tagging
- [ACL2017]Adversarial Multi-Criteria Learning for Chinese Word Segmentation
- 笔记-2004-Adaptive Chinese Word Segmentation
- A Gap-Based Framework for Chinese Word Segmentation via Very Deep Convolutional Network
- 笔记-2011-A New Unsupervised Approach to Word Segmentation
- 论文笔记——Rich feature hierarchies for accurate object detection and semantic segmentation
- 《Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification》阅读笔记
- 论文笔记--Fully Convolutional Networks for Semantic Segmentation
- 【论文笔记】Fully Convolutional Networks for Semantic Segmentation
- [深度学习论文笔记][Semantic Segmentation] Fully Convolutional Networks for Semantic Segmentation
- [Paper 学习笔记] Multi-Scale 3D Convolutional Neural Networks for Lesion Segmentation in Brain MRI
- How To Use WordBasic Functions in an MFC Automation Client for Word 97, Word 2000, Word 2002, or Word 2003
- 【转】R-CNN学习笔记2:Rich feature hierarchies for accurate object detection and semantic segmentation
- 论文笔记之:A CNN Cascade for Landmark Guided Semantic Part Segmentation
- 全卷积(FCN)论文阅读笔记:Fully Convolutional Networks for Semantic Segmentation
- 论文笔记:Research and Implementation of a Multi-label Learning Algorithm for Chinese Text Classification