📄 index.html
字号:
<html>
<head>
<meta http-equiv="Content-Language" content="zh-cn">
<meta http-equiv="Content-Type" content="text/html; charset=gb2312">
<meta name="GENERATOR" content="Microsoft FrontPage 4.0">
<meta name="ProgId" content="FrontPage.Editor.Document">
<title>计算所汉语词法分析系统ICTCLAS</title>
<meta name="Microsoft Theme" content="blends 011">
</head>
<body background="images/blegtext.gif" bgcolor="#CCCCCC" text="#000000" link="#993300" vlink="#0000FF" alink="#FF9900">
<!--mstheme--><font face="宋体">
<p><img border="0" src="images/logo1.jpg" width="226" height="80"><img border="0" src="images/logo2.jpg" width="112" height="79"><img border="0" src="images/logo3.jpg" width="160" height="79"></p>
<p align="center"><font face="隶书" size="4" color="#800080"><b>计算所汉语词法分析系统ICTCLAS</b> </font>
<a href="English.html">English</a>
</p>
<!--mstheme--></font>
<table cellSpacing="0" cellPadding="3" width="627" border="0" height="1">
<tbody>
<tr vAlign="bottom">
<td class="mbody" align="center" width="205" style="border-style: double; border-color: #0000FF" height="13"><!--mstheme--><font face="宋体"><a href="author.html">作者介绍</a><!--mstheme--></font></td>
<td class="mbody" align="left" width="963" rowspan="6" height="1"><!--mstheme--><font face="宋体">
<p style="margin-top: 0; margin-bottom: 0"><span style="font-size: 10.5pt; mso-bidi-font-size: 12.0pt; font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; font-weight: normal"> </span><span style="mso-bidi-font-size: 12.0pt; font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; font-weight: normal"><font size="3">
<span style="font-family: 宋体; mso-bidi-font-size: 12.0pt; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; font-weight: normal">词是最小的能够独立活动的有意义的语言成分,但汉语是以字为基本的书写单位,词语之间没有明显的区分标记,因此,中文词法分析是中文信息处理的基础与关键。为此,我们中国科学院计算技术研究所在多年研究基础上,耗时一年研制出了基于多层隐马模型的汉语词法分析系统ICTCLAS(Institute
of Computing Technology, Chinese Lexical Analysis System),该系统的功能有:中文分词;词性标注;未登录词识别。分词正确率高达97.58%(最近的973专家组评测结果),基于角色标注的未登录词识别能取得高于90%召回率,其中中国人名的识别召回率接近98%,分词和词性标注处理速度为31.5KB/s。</span></font></span></p>
<p style="margin-top: 0; margin-bottom: 0"><span style="mso-bidi-font-size: 12.0pt; font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; font-weight: normal"><font size="3"><span style="font-family: 宋体; mso-bidi-font-size: 12.0pt; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; font-weight: normal">
ICTCLAS所有的源代码、论文和技术文档都可以在<a href="http://www.nlp.org.cn/project/project.php?proj_id=6">www.nlp.org.cn</a></span>
<span style="font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; mso-bidi-font-size: 12.0pt; font-weight: normal">或者</span>
<a href="http://www.ict.ac.cn/freeware/003_ictclas.asp">www.ict.ac.cn/freeware/</a><span style="font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; mso-bidi-font-size: 12.0pt; font-weight: normal">上免费得到。</span>ICTCLAS<span style="font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; mso-bidi-font-size: 12.0pt; font-weight: normal">和计算所其他</span>14<span style="font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; mso-bidi-font-size: 12.0pt; font-weight: normal">项免费发布的成果被中外媒体广泛地报道,截止到</span>9<span style="font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; mso-bidi-font-size: 12.0pt; font-weight: normal">月,</span>ICTCLAS<span style="font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; mso-bidi-font-size: 12.0pt; font-weight: normal">被来自于中国、日本、新加坡、韩国、美国以及其他国家和地区的</span>2000<span style="font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; mso-bidi-font-size: 12.0pt; font-weight: normal">多位研究人员和商业机构下载使用。我们为免费发布</span>ICTCLAS<span style="font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; mso-bidi-font-size: 12.0pt; font-weight: normal">并能帮助用户解决中文词法问题而深感荣幸!</span></font></span></p>
<p class="MsoTitle" style="text-align: justify; text-justify: inter-ideograph; text-indent: 21.0pt; margin-top: 0; margin-bottom: 0"><span style="mso-bidi-font-size: 12.0pt; font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; font-weight: normal"><font size="3">另外,我们还提供一套完整的动态连接库<span style="mso-bidi-font-size: 12.0pt; font-weight: normal; font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman">ICTCLAS.dll</span>供开发者直接在自己的系统中调用<span style="mso-bidi-font-size: 12.0pt; font-weight: normal; font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman">ICTCLAS</span>来实现汉语词法分析。最后我们欢迎各位提出的任何问题,评述或者建议。<o:p>
</o:p>
</font></span></p>
<p style="margin-top: 0; margin-bottom: 0"><span style="mso-bidi-font-size: 12.0pt; font-family: 宋体; mso-ascii-font-family: Times New Roman; mso-hansi-font-family: Times New Roman; font-weight: normal"><font size="3">
在该系统的学习训练阶段采用了人民日报一个月的切分标注好的语料库,在此对人民日报、北大计算语言所、北京富士通公司表示感谢!欢迎相关领域的工程技术人员、研究人员使用,并提供宝贵意见。</font></span></p>
<p style="margin-top: 0; margin-bottom: 0"><font face="幼圆"><font color="#800080"><b>Author:
</b></font> Kevin
Zhang (张华平);
Qun Liu(刘群)</font></p>
<p style="margin-top: 0; margin-bottom: 0"><font face="幼圆">Inst.
of Computing Tech., Chinese Academy of Sciences</font></p>
<p style="margin-top: 0; margin-bottom: 0"><font face="幼圆"><font color="#800080"><b>Email:</b></font>
zhanghp@software.ict.ac.cn<o:p>
</o:p>
</font></p>
<p style="margin-top: 0; margin-bottom: 0"><font face="幼圆"><font color="#800080"><b>Tel:
</b></font>
+86-10-88455001/5/7 to 714</font><!--mstheme--></font></td>
</tr>
<tr vAlign="bottom">
<td class="mbody" align="center" width="205" style="border-style: double; border-color: #0000FF" height="1"><!--mstheme--><font face="宋体"><a href="Codes%20and%20Application/ICTCLAS_Win.exe">ICTCLAS</a><!--mstheme--></font></td>
</tr>
<tr vAlign="bottom">
<td class="mbody" align="center" width="205" style="border-style: double; border-color: #0000FF" height="1"><!--mstheme--><font face="宋体"><a href="codes.html">源代码</a><!--mstheme--></font></td>
</tr>
<tr vAlign="bottom">
<td class="mbody" align="center" width="205" style="border-style: double; border-color: #0000FF" height="1"><!--mstheme--><font face="宋体"><a href="Docs/自然语言处理开放资源许可证.doc">使用许可</a><!--mstheme--></font></td>
</tr>
<tr vAlign="bottom">
<td class="mbody" align="center" width="205" style="border-style: double; border-color: #0000FF" height="1"><!--mstheme--><font face="宋体"><a href="documents.html">相关文档</a><!--mstheme--></font></td>
</tr>
<tr vAlign="bottom">
<td class="mbody" align="center" width="205" style="border-style: double; border-color: #0000FF" height="16"><!--mstheme--><font face="宋体"><a href="http://mtgroup.ict.ac.cn/~zhp/ICTCLAS.htm">最新进展</a><!--mstheme--></font></td>
</tr>
</tbody>
</table>
<!--mstheme--><font face="宋体"><p>
</p>
<!--msthemeseparator--><p align="center"><img src="images/blesepa.gif"></p>
<p><center>[<a href="mailto:%20zhanghp@software.ict.ac.cn">跟我们联系</a>|<a href="http://www.nlp.org.cn/project/project.php?proj_id=6">参与开放项目</a>|<a href="http://mtgroup.ict.ac.cn">返回主页</a>]</center></p>
<CENTER>Copyright©2002 软件室mtgroup版权所有</CENTER><!--mstheme--></font>
</body>
</html>
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -