Wow, I must be tired. I had made the changes on my laptop, so had them right here and have just committed them.
Apologies for being bad about the JIRA issues -- will try to create those directly in the future. Jason On Wed, Apr 13, 2011 at 10:25 PM, Jason Baldridge <[email protected]>wrote: > Oops, I'll only be able to commit the code updates in the morning. JIRAs > have been created. > > > On Wed, Apr 13, 2011 at 10:17 PM, Jason Baldridge < > [email protected]> wrote: > >> Sorry, I got into a very busy spell there and didn't even read the rest of >> the thread because it was on my stack... >> >> I'll add the JIRAs and commit the code updates. >> >> Jason >> >> >> On Tue, Apr 12, 2011 at 12:15 PM, Jörn Kottmann <[email protected]>wrote: >> >>> Jason, >>> >>> can you give me a short update about these changes, >>> should we go ahead with the release, or is this something you >>> really need in it? >>> >>> If not, I would build RC 6 and do the vote. >>> >>> Thanks, >>> Jörn >>> >>> >>> On 4/11/11 2:25 PM, Jörn Kottmann wrote: >>> >>>> On 4/11/11 2:11 PM, Jason Baldridge wrote: >>>> >>>>> As it turns out, I found some issues with the way perceptron output was >>>>> normalized. It was sort of a strange way to handle negative numbers that >>>>> didn't really work, so I changed it to exponentiation and then >>>>> normalization. >>>>> >>>>> >>>> Can you please open a jira for this issue, and maybe give us a reference >>>> to the code? >>>> >>>> Also, the training accuracies reported during perceptron training were >>>>> much higher than final training accuracy, which turned out to be an >>>>> artifact >>>>> of the way training examples were ordered. I changed this so that after >>>>> each >>>>> iteration, the training accuracy is scored without changing the >>>>> parameters. >>>>> This gives a coherent value reported on every iteration, and it also >>>>> allows >>>>> early stopping by checking whether the same accuracy has been obtained for >>>>> some number of times (e.g. 4) in a row. (This could also be done by >>>>> checking >>>>> that parameter values haven't changed, which would be better, but which >>>>> I'd >>>>> only want to do after refactoring.) >>>>> >>>>> Please also make a jira for this one. >>>> >>>> I'm going to test the changes on a bunch of datasets this evening. If >>>>> anyone else is using the perceptrons much, it would be good if they could >>>>> do >>>>> a before and after comparison. >>>>> >>>> >>>> We only use the perceptron for the POSTagger currently, we can re-run >>>> the accuracy we get on >>>> some training/test sets. >>>> >>>> Jörn >>>> >>> >>> >> >> >> -- >> Jason Baldridge >> Assistant Professor, Department of Linguistics >> The University of Texas at Austin >> http://www.jasonbaldridge.com >> http://twitter.com/jasonbaldridge >> >> >> > > > -- > Jason Baldridge > Assistant Professor, Department of Linguistics > The University of Texas at Austin > http://www.jasonbaldridge.com > http://twitter.com/jasonbaldridge > > > -- Jason Baldridge Assistant Professor, Department of Linguistics The University of Texas at Austin http://www.jasonbaldridge.com http://twitter.com/jasonbaldridge
