📄 ictclas_api.htm
字号:
</td>
</tr>
</table>
</div>
<p class="MsoNormal" style="text-indent:10.5pt;mso-char-indent-count:1.0;
mso-char-indent-size:10.5pt"><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">表</span><span lang="EN-US">3.
ICTCLAS</span><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">在</span><span lang="EN-US">973</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman"">评测中的测试结果</span></p>
<p class="MsoNormal" style="text-indent:9.0pt;mso-char-indent-count:1.0;
mso-char-indent-size:9.0pt"><span style="font-size:9.0pt;mso-bidi-font-size:
12.0pt;font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">说明:</span><span lang="EN-US" style="font-size:9.0pt;
mso-bidi-font-size:12.0pt"><o:p>
</o:p>
</span></p>
<p class="MsoNormal" style="text-indent:9.0pt;mso-char-indent-count:1.0;
mso-char-indent-size:9.0pt"><span lang="EN-US" style="font-size:9.0pt;mso-bidi-font-size:
12.0pt">1)</span><span lang="EN-US" style="font-family:宋体"> </span><span style="font-size:9.0pt;mso-bidi-font-size:12.0pt;font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">数据来源:国家</span><span lang="EN-US" style="font-size:9.0pt;mso-bidi-font-size:12.0pt">973</span><span style="font-size:9.0pt;mso-bidi-font-size:12.0pt;font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">英汉机器翻译第二阶段评测的评测总结报告;</span><span lang="EN-US" style="font-size:9.0pt;mso-bidi-font-size:12.0pt"><o:p>
</o:p>
</span></p>
<p class="MsoNormal" style="text-indent:9.0pt;mso-char-indent-count:1.0;
mso-char-indent-size:9.0pt"><span lang="EN-US" style="font-size:9.0pt;mso-bidi-font-size:
12.0pt">2) </span><span style="font-size:9.0pt;mso-bidi-font-size:12.0pt;
font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">标注相对正确率</span><span lang="EN-US" style="font-size:9.0pt;
mso-bidi-font-size:12.0pt;font-family:宋体">RTAG=TAG1/SEG*100%</span><span lang="EN-US" style="font-size:9.0pt;mso-bidi-font-size:12.0pt"><o:p>
</o:p>
</span></p>
<p class="MsoNormal" style="text-indent:9.0pt;mso-char-indent-count:1.0;
mso-char-indent-size:9.0pt"><span lang="EN-US" style="font-size:9.0pt;mso-bidi-font-size:
12.0pt">3) </span><span style="font-size:9.0pt;mso-bidi-font-size:12.0pt;
font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">由于我们采取的词性标注集和</span><span lang="EN-US" style="font-size:9.0pt;
mso-bidi-font-size:12.0pt">973</span><span style="font-size:9.0pt;mso-bidi-font-size:
12.0pt;font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">专家组的标注集有较大出入,所以词性标注的正确率不具可比性。</span><span lang="EN-US" style="font-size:9.0pt;mso-bidi-font-size:12.0pt"><o:p>
</o:p>
</span></p>
<p class="MsoNormal" style="text-indent:21.0pt;mso-char-indent-count:2.0;
mso-char-indent-size:10.5pt"><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">专家组的开放评测结果表明:基于</span><span lang="EN-US">HHMM</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman"">的</span><span lang="EN-US">ICTCLAS</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">能实际的解决汉语词法分析问题,和兄弟单位的类似系统对比,</span><span lang="EN-US">ICTCLAS</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">的分词结果表现出色。</span></p>
<h3><a name="acl"><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">第一届国际分词大赛的评测结果</span></a></h3>
<p class="MsoNormal" style="text-indent:21.0pt;mso-char-indent-count:2.0;
mso-char-indent-size:10.5pt"><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">为了比较和评价不同方法和系统的性能,第四十一届国际计算语言联合会</span><span lang="EN-US">(41st
Annual Meeting of the Association for Computational Linguistics, 41th ACL )</span><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">下设的汉语特别兴趣研究组</span><span lang="EN-US">(the
ACL Special Interest Group on Chinese Language Processing, SIGHAN</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman"">;</span><span lang="EN-US">www.sighan.org)
</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman"">于</span><span lang="EN-US">2003</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">年</span><span lang="EN-US">4</span><span style="font-family:
宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman"">月</span><span lang="EN-US">22</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman"">日至</span><span lang="EN-US">25</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">日举办了第一届国际汉语分词评测大赛</span><span lang="EN-US">(First
International Chinese Word Segmentation Bakeoff)<sup>[28]</sup></span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">。报名参赛的分别是来自于大陆、台湾、美国等</span><span lang="EN-US">6</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">个国家和地区,共计</span><span lang="EN-US">19</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">家研究机构,最终提交结果的是</span><span lang="EN-US">12</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">家参赛队伍。</span></p>
<p class="MsoNormal" align="left" style="text-align:left;text-indent:21.0pt;
mso-char-indent-count:2.0;mso-char-indent-size:10.5pt;mso-layout-grid-align:
none;text-autospace:none"><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">大赛采取大规模语料库测试,进行综合打分的方法,语料库和标准分别来自北京大学(简体版)、宾州树库(简体版)、香港城市大学(繁体版),台湾“中央院”</span>
<span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">(繁体版)。每家标准分两个任务</span><span lang="EN-US">(Track)</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">:受限训练任务</span><span lang="EN-US">(Close
Track)</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">和非受限训练任务</span><span lang="EN-US">(Open
Track)</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">。</span></p>
<p class="MsoNormal" style="text-indent:21.0pt;mso-char-indent-count:2.0;
mso-char-indent-size:10.5pt"><span lang="EN-US">ICTCLAS</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">分别参加了简体的所有四项任务,和繁体的受限训练任务。其中在宾州树库受限训练任务中综合得分</span><span lang="EN-US" style="font-size:11.0pt;mso-font-kerning:0pt">0.881</span><sup><span lang="EN-US">[28]</span></sup><span style="font-size:11.0pt;font-family:宋体;
mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";
mso-font-kerning:0pt">,名列第一;</span><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">北京大学受限训练任务中综合得分</span><span lang="EN-US" style="font-size:11.0pt;mso-font-kerning:0pt">0.951</span><sup><span lang="EN-US">[28]</span></sup><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">,</span><span style="font-size:11.0pt;font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman";mso-font-kerning:0pt">名列第一;</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">北京大学受限训练任务中综合得分</span><span lang="EN-US" style="font-size:
11.0pt;mso-font-kerning:0pt">0.953</span><sup><span lang="EN-US">[28]</span></sup><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">,</span><span style="font-size:11.0pt;font-family:宋体;
mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";
mso-font-kerning:0pt">名列第二。值得注意的是,我们在短短的两天之内,采取</span><span lang="EN-US" style="font-size:11.0pt;mso-font-kerning:0pt">ICTCLAS</span><span style="font-size:11.0pt;font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman";mso-font-kerning:0pt">简体版的内核代码,将多层隐马模型推广到繁体分词当中,同样取得了</span><span lang="EN-US" style="font-size:11.0pt;mso-font-kerning:0pt">0.938</span><sup><span lang="EN-US">[28]</span></sup><span style="font-size:11.0pt;font-family:宋体;
mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";
mso-font-kerning:0pt">的综合得分。</span></p>
<p>>><span style="font-family: 宋体; mso-ascii-font-family: 'MS Song\'', '\000B \'', Beijing; mso-hansi-font-family: 'MS Song\'', '\000B \'', Beijing"><a href="#chap1">Back</a>
</span>>|<span style="font-family: 宋体; mso-ascii-font-family: 'MS Song\'', '\000B \'', Beijing; mso-hansi-font-family: 'MS Song\'', '\000B \'', Beijing"><a href="#header">Top</a></span></p>
<P>[Hua-Ping Zhang 2003 : Chapter 1 - Introduction / 4]
</P>
<h2><a name="Dairly"><span lang="EN-US">ICTCLAS</span></a><span style="font-family: 黑体; mso-ascii-font-family: Arial; mso-ansi-language: EN; mso-bookmark: _Toc51384097">大事记:</span><span lang="EN" style="mso-ansi-language:EN"><o:p>
</o:p>
</span></h2>
<p class="MsoNormal" style="margin-left:18.0pt;text-indent:-18.0pt;mso-list:l6 level1 lfo3;
tab-stops:list 18.0pt"><span lang="EN" style="mso-ansi-language:
EN">1)<span style="font:7.0pt "Times New Roman""> </span></span><span lang="EN" style="mso-ansi-language:EN">2002</span><span style="font-family:宋体;
mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";
mso-ansi-language:EN">年</span><span lang="EN" style="mso-ansi-language:EN">7</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman";mso-ansi-language:EN">月,在</span><span lang="EN" style="mso-ansi-language:EN">973</span><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman";mso-ansi-language:
EN">项目</span><span lang="EN" style="mso-ansi-language:EN">"</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman";mso-ansi-language:EN">图像、语音、自然语言理解与知识挖掘</span><span lang="EN" style="mso-ansi-language:EN">"</span><span style="font-family:宋体;
mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";
mso-ansi-language:EN">专家组的评测中,在所有参评的系统中,评测得分最高。</span><span style="font-family:
宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman"">(</span><span style="font-family:宋体;mso-ascii-font-family:"MS Song\, \000B\, Beijing";
mso-hansi-font-family:"MS Song\, \000B\, Beijing"">分词正确率高达</span><span lang="EN-US" style="font-family:"MS Song\, \000B\, Beijing"">97.58%</span><span style="font-family:宋体;mso-ascii-font-family:"MS Song\, \000B\, Beijing";
mso-hansi-font-family:"MS Song\, \000B\, Beijing"">,</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman"">参赛单位包括北京大学,清华大学等)</span><span lang="EN" style="mso-ansi-language:
EN"><o:p>
</o:p>
</span></p>
<p class="MsoNormal" style="margin-left:18.0pt;text-indent:-18.0pt;mso-list:l6 level1 lfo3;
tab-stops:list 18.0pt"><span lang="EN-US" style="mso-hansi-font-family:
宋体">2)<span style="font:7.0pt "Times New Roman""> </span></span><span lang="EN" style="mso-ansi-language:EN">2003</span><span style="font-family:宋体;
mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";
mso-ansi-language:EN">年</span><span lang="EN" style="mso-ansi-language:EN">1</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman";mso-ansi-language:EN">月</span><span lang="EN" style="mso-ansi-language:
EN">7</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman";mso-ansi-language:EN">日,获得国家版权局授予的软件著作权登记证书,编号为软著登字</span><span lang="EN" style="mso-ansi-language:EN">005178</span><span style="font-family:
宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";
mso-ansi-language:EN">号</span><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman"">)</span><span lang="EN-US" style="mso-hansi-font-family:宋体"><o:p>
</o:p>
</span></p>
<p class="MsoNormal" style="margin-left:18.0pt;text-indent:-18.0pt;mso-list:l6 level1 lfo3;
tab-stops:list 18.0pt"><span lang="EN-US" style="mso-hansi-font-family:
宋体">3)<span style="font:7.0pt "Times New Roman""> </span></span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman";mso-ansi-language:EN">在</span><span lang="EN" style="mso-ansi-language:
EN">2003</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman";mso-ansi-language:EN">年</span><span lang="EN" style="mso-ansi-language:EN">4</span><span style="font-family:宋体;
mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";
mso-ansi-language:EN">月</span><span lang="EN" style="mso-ansi-language:EN">22</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:
"Times New Roman";mso-ansi-language:EN">日至</span><span lang="EN" style="mso-ansi-language:EN">25</span><span style="font-family:宋体;mso-ascii-font-family:
"Times New Roman";mso-hansi-font-family:"Times New Roman";mso-ansi-language:
EN">日</span><span style="font-family:宋体;mso-ascii-font-family:"Times New Roman";
mso-hansi-font-family:"Times New Roman"">,</span><span lang="EN" style="mso-ansi-language:EN">
ICTCLAS</span><span style="font-family:宋体;
mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";
mso-ansi-language:EN">参加了第四十一届国际计算语言联合会</span><span lang="EN" style="mso-ansi-language:
EN">(41st Annual Meeting of the Association for Computational Linguistics,<span style="mso-spacerun: yes">&n
⌨️ 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 + -