从文本中提取关键短语（1-4 个单词的 ngram）

Question

从文本块中提取关键短语的最佳方法是什么？我正在编写一个工具来进行关键字提取：类似这样的。我找到了一些用于 Python 和 Perl 的库来提取 n 元语法，但我是在 Node 中编写的，所以我需要一个 JavaScript 解决方案。如果没有任何现有的 JavaScript 库，有人可以解释如何执行此操作，以便我可以自己编写吗？

Answer 1

我喜欢这个想法，所以我已经实现了它：请参阅下文（包括描述性注释）。
预览地址：https://jsfiddle.net/WsKMx

/*@author Rob W, created on 16-17 September 2011, on request for Stackoverflow (http://stackoverflow.com/q/7085454/938089)
 * Modified on 17 juli 2012, fixed IE bug by replacing [,] with [null]
 * This script will calculate words. For the simplicity and efficiency,
 * there's only one loop through a block of text.
 * A 100% accuracy requires much more computing power, which is usually unnecessary
 **/


var text = "A quick brown fox jumps over the lazy old bartender who said 'Hi!' as a response to the visitor who presumably assaulted the maid's brother, because he didn't pay his debts in time. In time in time does really mean in time. Too late is too early? Nonsense! 'Too late is too early' does not make any sense.";

var atLeast = 2;       // Show results with at least .. occurrences
var numWords = 5;      // Show statistics for one to .. words
var ignoreCase = true; // Case-sensitivity
var REallowedChars = /[^a-zA-Z'\-]+/g;
 // RE pattern to select valid characters. Invalid characters are replaced with a whitespace

var i, j, k, textlen, len, s;
// Prepare key hash
var keys = [null]; //"keys[0] = null", a word boundary with length zero is empty
var results = [];
numWords++; //for human logic, we start counting at 1 instead of 0
for (i=1; i<=numWords; i++) {
    keys.push({});
}

// Remove all irrelevant characters
text = text.replace(REallowedChars, " ").replace(/^\s+/,"").replace(/\s+$/,"");

// Create a hash
if (ignoreCase) text = text.toLowerCase();
text = text.split(/\s+/);
for (i=0, textlen=text.length; i<textlen; i++) {
    s = text[i];
    keys[1][s] = (keys[1][s] || 0) + 1;
    for (j=2; j<=numWords; j++) {
        if(i+j <= textlen) {
            s += " " + text[i+j-1];
            keys[j][s] = (keys[j][s] || 0) + 1;
        } else break;
    }
}

// Prepares results for advanced analysis
for (var k=1; k<=numWords; k++) {
    results[k] = [];
    var key = keys[k];
    for (var i in key) {
        if(key[i] >= atLeast) results[k].push({"word":i, "count":key[i]});
    }
}

// Result parsing
var outputHTML = []; // Buffer data. This data is used to create a table using `.innerHTML`

var f_sortAscending = function(x,y) {return y.count - x.count;};
for (k=1; k<numWords; k++) {
    results[k].sort(f_sortAscending);//sorts results
    
    // Customize your output. For example:
    var words = results[k];
    if (words.length) outputHTML.push('<td colSpan="3" class="num-words-header">'+k+' word'+(k==1?"":"s")+'</td>');
    for (i=0,len=words.length; i<len; i++) {
        
        //Characters have been validated. No fear for XSS
        outputHTML.push("<td>" + words[i].word + "</td><td>" +
           words[i].count + "</td><td>" +
           Math.round(words[i].count/textlen*10000)/100 + "%</td>");
           // textlen defined at the top
           // The relative occurence has a precision of 2 digits.
    }
}
outputHTML = '<table id="wordAnalysis"><thead><tr>' +
              '<td>Phrase</td><td>Count</td><td>Relativity</td></tr>' +
              '</thead><tbody><tr>' +outputHTML.join("</tr><tr>")+
               "</tr></tbody></table>";
document.getElementById("RobW-sample").innerHTML = outputHTML;
/*
CSS:
#wordAnalysis td{padding:1px 3px 1px 5px}
.num-words-header{font-weight:bold;border-top:1px solid #000}

HTML:
<div id="#RobW-sample"></div>
*/

Answer 2

我不知道 JavaScript 中有这样的库，但逻辑是

1. 将文本拆分为数组
2. ，然后排序和计数，

或者

1. 拆分为数组
2. 创建一个辅助数组，
3. 遍历第一个数组的每个项目，
4. 检查当前项目是否存在于辅助数组中（
5. 如果不存在）
   项目的键推送
6. 将其作为其他
   增加寻找物品的钥匙=的价值。
   HTH

伊沃·斯托伊科夫

Answer 3

function ngrams(seq, n) {
  to_return = []
  for (let i=0; i<seq.length-(n-1); i++) {
      let cur = []
      for (let j=i; j<seq.length && j<=i+(n-1); j++) {
          cur.push(seq[j])
      }
      to_return.push(cur.join(''))
  }
  return to_return
}

> ngrams(['a', 'b', 'c'], 2)
['ab', 'bc']