参考链接:
https://github.com/HIT-SCIR/ltp/blob/master/doc/install.rst
http://www.xfyun.cn/index.php/services/ltp/detail?&app_id=NTZmYzg5ZWE=
http://www.ltp-cloud.com/document/#api_rest_format_json
其他分词算法参考链接:
NLPIR:http://www.nlpir.org/ http://www.datatang.com/data/13483
bosonnlp: http://bosonnlp.com/
下面针对LTP分词算法 实践
1.登录官网 获取授权码api_key
2.分词接口操作
接口参数:
StringBuilder sb = new StringBuilder(); sb.Append(" 本报讯 (记者 王少勇)3月28日,国土资源部部长、党组书记、国家土地总督察姜大明主持召开第10次部党组会议,传达学习习xx总书记在北京市考察工作时的重要讲话精神。会议提出,要深刻理解习xx总书记重要讲话精神,充分发挥国土资源部门的服务和保障作用,推进京津冀协同发展。 xx平总书记高度重视北京发展和京津冀协同发展,今年2月下旬专程到北京市调研考察,并发表重要讲话,从做好北京发展和管理工作、推动京津冀协同发展两个方面进行了深刻阐述。会议指出,习xx总书记的重要讲话,对于实现京津冀优势互补、促进环渤海经济区发展、带动北方腹地发展,意义重大、影响深远,要认真学习,深刻领会。 会议提出,国土资源部门要进一步解放思想,加大改革创新力度,"); string url = "http://ltpapi.voicecloud.cn/analysis/"; string data = "api_key=xxx&text=" + sb.ToString() + "&pattern=ws&format=xml"; string returnValue= HttpHelper.HttpPost(url,data); Console.WriteLine(returnValue); Console.ReadKey();
/// <summary> /// Post请求 webClient /// </summary> /// <param name="Url">地址</param> /// <param name="postString">这里即为传递的参数,可以用工具抓包分析,也可以自己分析,主要是form里面每一个name都要加进来 </param> /// <returns></returns> public static string HttpPost(string url, string postString) { byte[] postData = Encoding.UTF8.GetBytes(postString);//编码,尤其是汉字,事先要看下抓取网页的编码方式 WebClient webClient = new WebClient(); webClient.Headers.Add("Content-Type", "application/x-www-form-urlencoded");//采取POST方式必须加的header,如果改为GET方式的话就去掉这句话即可 byte[] responseData = webClient.UploadData(url, "POST", postData);//得到返回字符流 string srcString = Encoding.UTF8.GetString(responseData);//解码 return srcString; }
3.测试结果
<?xml version="1.0" encoding="utf-8" ?> <xml4nlp> <note sent="y" word="y" pos="n" ne="n" parser="n" wsd="n" srl="n" /> <doc> <para id="0"> <sent id="0" cont="本报讯 (记者 王少勇)3月28日,国土资源部部长、党 组书记、国家土地总督察姜大明主持召开第10次部党组会议,传达学习习xx总书记在北京 市考察工作时的重要讲话精神。"> <word id="0" cont="本报" /> <word id="1" cont="讯" /> <word id="2" cont="(" /> <word id="3" cont="记者" /> <word id="4" cont="王少勇" /> <word id="5" cont=")" /> <word id="6" cont="3月" /> <word id="7" cont="28日" /> <word id="8" cont="," /> <word id="9" cont="国土" /> <word id="10" cont="资源部" /> <word id="11" cont="部长" /> <word id="12" cont="、" /> <word id="13" cont="党组" /> <word id="14" cont="书记" /> <word id="15" cont="、" /> <word id="16" cont="国家" /> <word id="17" cont="土地" /> <word id="18" cont="总督" /> <word id="19" cont="察姜" /> <word id="20" cont="大明" /> <word id="21" cont="主持" /> <word id="22" cont="召开" /> <word id="23" cont="第10" /> <word id="24" cont="次" /> <word id="25" cont="部党组" /> <word id="26" cont="会议" /> <word id="27" cont="," /> <word id="28" cont="传达" /> <word id="29" cont="学习" /> <word id="30" cont="习" /> <word id="31" cont="近平" /> <word id="32" cont="总书记" /> <word id="33" cont="在" /> <word id="34" cont="北京市" /> <word id="35" cont="考察" /> <word id="36" cont="工作" /> <word id="37" cont="时" /> <word id="38" cont="的" /> <word id="39" cont="重要" /> <word id="40" cont="讲话" /> <word id="41" cont="精神" /> <word id="42" cont="。" /> </sent> <sent id="1" cont="会议提出,要深刻理解习xx总书记重要讲话精神,充 分发挥国土资源部门的服务和保障作用,推进京津冀协同发展。"> <word id="0" cont="会议" /> <word id="1" cont="提出" /> <word id="2" cont="," /> <word id="3" cont="要" /> <word id="4" cont="深刻" /> <word id="5" cont="理解" /> <word id="6" cont="习" /> <word id="7" cont="近平" /> <word id="8" cont="总书记" /> <word id="9" cont="重要" /> <word id="10" cont="讲话" /> <word id="11" cont="精神" /> <word id="12" cont="," /> <word id="13" cont="充分" /> <word id="14" cont="发挥" /> <word id="15" cont="国土" /> <word id="16" cont="资源" /> <word id="17" cont="部门" /> <word id="18" cont="的" /> <word id="19" cont="服务" /> <word id="20" cont="和" /> <word id="21" cont="保障" /> <word id="22" cont="作用" /> <word id="23" cont="," /> <word id="24" cont="推进" /> <word id="25" cont="京" /> <word id="26" cont="津" /> <word id="27" cont="冀" /> <word id="28" cont="协同" /> <word id="29" cont="发展" /> <word id="30" cont="。" /> </sent> <sent id="2" cont="习xx总书记高度重视北京发展和京津冀协同发展,今 年2月下旬专程到北京市调研考察,并发表重要讲话,从做好北京发展和管理工作、推动京 津冀协同发展两个方面进行了深刻阐述。"> <word id="0" cont="习" /> <word id="1" cont="近平" /> <word id="2" cont="总书记" /> <word id="3" cont="高度" /> <word id="4" cont="重视" /> <word id="5" cont="北京" /> <word id="6" cont="发展" /> <word id="7" cont="和" /> <word id="8" cont="京" /> <word id="9" cont="津" /> <word id="10" cont="冀" /> <word id="11" cont="协同" /> <word id="12" cont="发展" /> <word id="13" cont="," /> <word id="14" cont="今年" /> <word id="15" cont="2月" /> <word id="16" cont="下旬" /> <word id="17" cont="专程" /> <word id="18" cont="到" /> <word id="19" cont="北京市" /> <word id="20" cont="调研" /> <word id="21" cont="考察" /> <word id="22" cont="," /> <word id="23" cont="并" /> <word id="24" cont="发表" /> <word id="25" cont="重要" /> <word id="26" cont="讲话" /> <word id="27" cont="," /> <word id="28" cont="从" /> <word id="29" cont="做好" /> <word id="30" cont="北京" /> <word id="31" cont="发展" /> <word id="32" cont="和" /> <word id="33" cont="管理" /> <word id="34" cont="工作" /> <word id="35" cont="、" /> <word id="36" cont="推动" /> <word id="37" cont="京" /> <word id="38" cont="津" /> <word id="39" cont="冀" /> <word id="40" cont="协同" /> <word id="41" cont="发展" /> <word id="42" cont="两" /> <word id="43" cont="个" /> <word id="44" cont="方面" /> <word id="45" cont="进行" /> <word id="46" cont="了" /> <word id="47" cont="深刻" /> <word id="48" cont="阐述" /> <word id="49" cont="。" /> </sent> <sent id="3" cont="会议指出,习xx总书记的重要讲话,对于实现京津冀 优势互补、促进环渤海经济区发展、带动北方腹地发展,意义重大、影响深远,要认真学习 ,深刻领会。"> <word id="0" cont="会议" /> <word id="1" cont="指出" /> <word id="2" cont="," /> <word id="3" cont="习xx" /> <word id="4" cont="总书记" /> <word id="5" cont="的" /> <word id="6" cont="重要" /> <word id="7" cont="讲话" /> <word id="8" cont="," /> <word id="9" cont="对于" /> <word id="10" cont="实现" /> <word id="11" cont="京" /> <word id="12" cont="津" /> <word id="13" cont="冀" /> <word id="14" cont="优势" /> <word id="15" cont="互补" /> <word id="16" cont="、" /> <word id="17" cont="促进" /> <word id="18" cont="环" /> <word id="19" cont="渤海" /> <word id="20" cont="经济区" /> <word id="21" cont="发展" /> <word id="22" cont="、" /> <word id="23" cont="带动" /> <word id="24" cont="北方" /> <word id="25" cont="腹地" /> <word id="26" cont="发展" /> <word id="27" cont="," /> <word id="28" cont="意义" /> <word id="29" cont="重大" /> <word id="30" cont="、" /> <word id="31" cont="影响" /> <word id="32" cont="深远" /> <word id="33" cont="," /> <word id="34" cont="要" /> <word id="35" cont="认真" /> <word id="36" cont="学习" /> <word id="37" cont="," /> <word id="38" cont="深刻" /> <word id="39" cont="领会" /> <word id="40" cont="。" /> </sent> <sent id="4" cont="会议提出,国土资源部门要进一步解放思想,加大改革 创新力度,"> <word id="0" cont="会议" /> <word id="1" cont="提出" /> <word id="2" cont="," /> <word id="3" cont="国土" /> <word id="4" cont="资源" /> <word id="5" cont="部门" /> <word id="6" cont="要" /> <word id="7" cont="进一步" /> <word id="8" cont="解放思想" /> <word id="9" cont="," /> <word id="10" cont="加大" /> <word id="11" cont="改革" /> <word id="12" cont="创新" /> <word id="13" cont="力度" /> <word id="14" cont="," /> </sent> </para> </doc> </xml4nlp>
时间: 2024-11-09 06:43:11