EclipseCon 2007 March 5-8, Santa Clara California





Enhancing Content Assist using Machine Learning Techniques.

Rahul Kapoor (ThoughtWorks Inc)

· Demo

Thursday, 11:10, 50 minutes | Room 206

7
·
8
·
9
·
10
·
11
·
12
·
13
·
14
·
15
·
16
·
17
·
18
·
19

possible completions. This demo presents a language agnostic machine learning based Content Assist implementation. Learning based Content Assist works by creating a model of the language by training the Content Assist mechanism on a corpus of training source code and then using the model to make predictions as the user is entering source code in the editor. Objective evaluation metrics like key strokes per character achievable with this approach as well result of subjective evaluation on real world code is shown. The demo points out the additional possibilities opened up by using the learning based approach including completion inside string literals and comments, suggestion of variable names during definition and highly accurate multiple word completions among others. The approach presented uses a prediction model implementation based on variable order markov modeling specifically the popular Prediction by Partial Match method (PPM-C) algorithm. The full text of the paper with details can be found here.

Rahul is software developer with ThoughtWorks Inc and lives in Providence, Rhode Island.

Floor Plan

Gold sponsors

Ingres logo

BEA logo

IBM logo

Business Objects logo

Klocwork logo

Windriver logo

Red Hat logo

Actuate logo

Silver sponsors

Compuware logo

Sybase logo

Google logo

Nexaweb

Activegrid

Genuitec

Instantiations

Cloudsmith

Code Gear

ACCESS

Oracle

Telelogic

Innoopract logo

Lynux Works

Media sponsors

Eclipse Magazine logo

GoingtoMeet.com logo

Methods and Tools logo

Eclipsezone logo

Addison-Wesley logo

Eclipse Magazin logo

Embedded Computing logo

SD Times logo

Enterprise Open Source logo

ACM Queue logo

TheServerSide Java Symposium

Eclipse Review logo

Software Test & Performance logo

Eclipse Developers Journal logo

Eclipse Source logo