Revision: 16880
http://sourceforge.net/p/gate/code/16880
Author: adamfunk
Date: 2013-09-12 12:50:30 +0000 (Thu, 12 Sep 2013)
Log Message:
-----------
Source of current IDF formulae; to do item
Modified Paths:
--------------
gate/trunk/plugins/TermRaider/src/gate/termraider/bank/modes/IdfCalculation.java
Modified:
gate/trunk/plugins/TermRaider/src/gate/termraider/bank/modes/IdfCalculation.java
===================================================================
---
gate/trunk/plugins/TermRaider/src/gate/termraider/bank/modes/IdfCalculation.java
2013-09-12 12:46:02 UTC (rev 16879)
+++
gate/trunk/plugins/TermRaider/src/gate/termraider/bank/modes/IdfCalculation.java
2013-09-12 12:50:30 UTC (rev 16880)
@@ -16,6 +16,13 @@
Logarithmic,
LogarithmicPlus1;
+ /* These calculations are from Manning & Schütze, Foundations of
+ * Statistical NLP, section 15.2 (p.544).
+ *
+ * TODO: Use (df + 1) normalization methods so we can handle
+ * terms not found in the IDF table (to allow for external
+ * IDF sources in future use).
+ */
public static double calculate(IdfCalculation mode, int rawDF, int
corpusSize) {
double df = (double) rawDF;
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
------------------------------------------------------------------------------
How ServiceNow helps IT people transform IT departments:
1. Consolidate legacy IT systems to a single system of record for IT
2. Standardize and globalize service processes across IT
3. Implement zero-touch automation to replace manual, redundant tasks
http://pubads.g.doubleclick.net/gampad/clk?id=51271111&iu=/4140/ostg.clktrk
_______________________________________________
GATE-cvs mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/gate-cvs
