Extracting key phrases from an english text with golang

xuanbao · · 438 次点击    
这是一个分享于 的资源,其中的信息可能已经有所发展或是发生改变。
<p>Hi,</p> <p>Is there any module/package to extract key phrases from text with golang? As a key phrases i mean 2 or more words that are repeated together and are not common words. Some names, titles , 2-3 nouns etc.</p> <hr/>**评论:**<br/><br/>t_claudiu: <pre><p>Needed something like this a few months ago and the closest thing I came across for Named Entity Recognition was this:</p> <p><a href="https://github.com/sbl/ner" rel="nofollow">https://github.com/sbl/ner</a></p> <p>You could also do: <a href="https://github.com/advancedlogic/go-freeling" rel="nofollow">https://github.com/advancedlogic/go-freeling</a> or <a href="http://nlp.lsi.upc.edu/freeling/node/1" rel="nofollow">http://nlp.lsi.upc.edu/freeling/node/1</a> (it has an HTTP endpoint you can connect to).</p></pre>improbabble: <pre><p>The simplest approach to this is to use Mikolov&#39;s (creator of word2vec) <code>word2phrase</code> algorithm. I&#39;ve used it production a few times and people always like the results, it&#39;s simple to implement, needs minimal tuning and is fairly fast.</p> <ul> <li>Paper: <a href="http://papers.nips.cc/paper/5021-di" rel="nofollow">http://papers.nips.cc/paper/5021-di</a></li> <li>Orig C implementation: <a href="https://github.com/nicholas-leonard/word2vec/blob/master/word2phrase.c" rel="nofollow">https://github.com/nicholas-leonard/word2vec/blob/master/word2phrase.c</a></li> <li>Python implementation: <a href="https://github.com/travisbrady/word2phrase/blob/master/word2phrase.py" rel="nofollow">https://github.com/travisbrady/word2phrase/blob/master/word2phrase.py</a></li> </ul></pre>gelembjuk: <pre><p>This looks interesting. But will need implementation . I expected to find something ready :( </p></pre>improbabble: <pre><p>Well, there are lots of APIs that do this kind of thing too:</p> <ul> <li><a href="http://monkeylearn.com/" rel="nofollow">http://monkeylearn.com/</a></li> <li><a href="http://www.alchemyapi.com/products/demo/alchemylanguage" rel="nofollow">http://www.alchemyapi.com/products/demo/alchemylanguage</a></li> <li><a href="https://www.textrazor.com/" rel="nofollow">https://www.textrazor.com/</a></li> <li><a href="http://text-processing.com/docs/phrases.html" rel="nofollow">http://text-processing.com/docs/phrases.html</a></li> <li><a href="http://fivefilters.org/term-extraction/" rel="nofollow">http://fivefilters.org/term-extraction/</a></li> </ul></pre>

入群交流(和以上内容无关):加入Go大咖交流群,或添加微信:liuxiaoyan-s 备注:入群;或加QQ群:692541889

438 次点击  
加入收藏 微博
暂无回复
添加一条新回复 (您需要 登录 后才能回复 没有账号 ?)
  • 请尽量让自己的回复能够对别人有帮助
  • 支持 Markdown 格式, **粗体**、~~删除线~~、`单行代码`
  • 支持 @ 本站用户;支持表情(输入 : 提示),见 Emoji cheat sheet
  • 图片支持拖拽、截图粘贴等方式上传