從文本中提取關鍵短語（1-4個字節）

Question

從文本塊中提取關鍵短語的最佳方式是什麼？我正在編寫一個工具來執行關鍵字提取：something like this。我發現了幾個用於Python和Perl的庫來提取n-gram，但是我在Node中編寫這個庫，所以我需要一個JavaScript解決方案。如果沒有任何現有的JavaScript庫，有人可以解釋如何做到這一點，所以我可以自己寫嗎？

Answer 1

我喜歡這個主意，所以我實現它：見下文（描述性註釋包括）。
預覽在：http://fiddle.jshell.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

我不知道在JavaScript這樣的庫，但邏輯是

1. 拆分文本到數組
2. 然後進行排序和計數

或者

1. 分成數組
2. 創建輔助數組
3. 遍歷第一陣列的每個項目
4. 檢查在輔助陣列中是否存在
5. 當前項目，如果不存在 推它爲具有密鑰的項的鍵
6. 別的 增大值=所尋求的項目。 HTH

伊沃Stoykov