ZH cheese: Natural language processing Tool LTP language cloud how to call?

Objective

LTP Language Cloud Platform

Support Word segmentation, part-of-speech tagging, named entity recognition, dependency parsing, semantic role labeling ;

Support Custom Word segmentation (you provide the data after the word segmentation, it will help you to annotate), but does not support the custom vocabulary , Support C #, Go, Java, JavaScript, Nodejs, PHP, Python, R, Ruby and other language calls, and some error response, Frequency limits, important notes (which I have not used so far); text

Official website: http://www.ltp-cloud.com/

Working with Documents: http://www.ltp-cloud.com/document/

Online Demo: http://www.ltp-cloud.com/demo/

Various language invocation instances can be downloaded to GitHub: https://github.com/HIT-SCIR/ltp-cloud-api-tutorial

For example, Python version of: Https://github.com/HIT-SCIR/ltp-cloud-api-tutorial/tree/master/Python

STEP1: Register

Apply for an API key at this URL, which will be used later;

STEP2: A simple example (Python version)

(1) Copy code: Copy a piece of code from GitHub (depending on the language you use and the features you need)

(2) Modify the code:

<1> api_key = " yourapikey" in "Yourapikey" Modify the API Key for your STEP1 application;

<2> change the text = " I love Beijing tian ' an door" to the one you want to process;

<3> set different parameters according to the requirements (in fact, only need to Api_key,text,pattern,format Four parameters is enough, carefully look at the pattern):

　　　

#-*-coding:utf-8-*-#!/usr/bin/env python#This example shows how to use Python to access the LTP API to perform full#stack Chinese text analysis including word segmentation, POS tagging, dep-#endency parsing, name entity recognization and semantic role labeling and#get the result in specified format.ImportUrllib2, UrllibImportSYSif __name__=='__main__':    ifLen (SYS.ARGV) < 2orSYS.ARGV[1] not inch["XML","JSON","CONLL"]:        Print>> Sys.stderr,"usage:%s [XML/JSON/CONLL]"%Sys.argv[0] Sys.exit (1) Uri_base="http://ltpapi.voicecloud.cn/analysis/?"Api_key="Yourapikey"text="I love Beijing Tian ' an gate"    #Note that if your text contain special characters such as linefeed or ' & ',    #You need to use UrlEncode to encode your dataText =urllib.quote (text) format= Sys.argv[1] Pattern=" All"URL=(Uri_base+"api_key="+ Api_key +"&"+"text="+ text +"&"+"format="+ Format +"&"+"pattern="+" All")    Try: Response=urllib2.urlopen (URL) content=Response.read (). Strip ()PrintcontentexceptUrllib2. Httperror, E:Print>> Sys.stderr, E.reason

STEP3: Run

If you want to batch process txt or XML files, you need to write a batch of code, below is the one I used in the Project batch processing a directory TXT file code ( that is, add a layer of loops and set an output ):

1 #-*-coding:utf-8-*-2 #!/usr/bin/env python3 4 #This example shows how to use Python to access the LTP API to perform full5 #stack Chinese text analysis including word segmentation, POS tagging, dep-6 #endency parsing, name entity recognization and semantic role labeling and7 #get the result in specified format.8 9 ImportUrllib2, UrllibTen ImportSYS One  A if __name__=='__main__': -Uri_base ="http://ltpapi.voicecloud.cn/analysis/?" -Api_key ="7132g4z1he3s********dsxtncma1jscse5xumai" the  -f = open ("E:\\pyproj\\others\\rite_sentence.txt") -FW = Open ("E:\\pyproj\\others\\rite_pos.txt",'W') -  +line =F.readline () -      while(line): +Text = Line A         #Note that if your text contain special characters such as linefeed or ' & ', at         #You need to use UrlEncode to encode your data -Text =urllib.quote (text) -Format ="Plain" -Pattern ="POS" -  -URL =(Uri_base in+"api_key="+ Api_key +"&" -+"text="+ text +"&" to+"format="+ Format +"&" ++"pattern="+pattern) -  the         Try: *Response =urllib2.urlopen (URL) $Content =Response.read (). Strip ()Panax Notoginseng             Printcontent -Fw.write (line+content+'\ n') the         exceptUrllib2. Httperror, E: +             Print>>Sys.stderr, E.reason Aline =F.readline () the fw.close () +F.close ()

ZH cheese: Natural language processing Tool LTP language cloud how to call?