In the part of speech tagging tutorial, the command line should apparently be java -cp build/classes/:../../../lingpipe-3.7.0.jar RunMedPost...
677
Bob Carpenter
colloquialdo...
Apr 1, 2009 9:58 pm
Thanks for the note and the patch. We really want the tutorials to work as written, so any suggestions for patches are greatly appreciated. I'm in the final...
678
Bob Carpenter
colloquialdo...
Apr 17, 2009 4:12 am
LingPipe 3.8.0 is now available from the site: http://alias-i.com/lingpipe This is a big release — the details are available on the home page linked above. ...
679
Bob Carpenter
colloquialdo...
Apr 21, 2009 7:45 pm
I accidentally left an old description in the documentation on the LingPipe home page. We have not in fact deprecated util.FeatureExtractor as we said on the...
680
Rafael Cotta
rafaelcotta
Apr 22, 2009 2:30 pm
Hi, I am writing the specifications for my final assignment, that will use LinpPipe classification tools. Going through the tutorials I could find...
681
Bob Carpenter
colloquialdo...
Apr 22, 2009 5:02 pm
... Why do you want to do that? ... You can actually put the stemming inline using our tokenizers. Or you can preconvert it using whatever tool you want and...
682
Rafael Cotta
rafaelcotta
Apr 24, 2009 1:32 am
Hi, Bob I was going to reply to your email on this morning with more questions, but luckily I could get back from work, study a little more about this subject...
683
Rafael Cotta
rafaelcotta
Apr 24, 2009 10:02 am
Re-reading my emails I noticed that I didn't tell you all what exactly my final assignment is. I'll write a service to classify texts into predefined ...
684
reckb
Apr 28, 2009 3:00 pm
We need to report on LingPipe use in the field of biology as part of our NIH (The USA National Institutes of Health) funding. If you have used...
685
Bob Carpenter
colloquialdo...
Apr 29, 2009 7:34 pm
... The answer is probably "yes". In fact our evals show what the effect of various thresholds are on the one-versus-all subproblems if you look at the scored...
686
Bob Carpenter
colloquialdo...
Apr 29, 2009 7:46 pm
An anonymous bug reporter indicated the model: $LINGPIPE/demos/models/langid-leipzig.classifier was missing. I didn't realize it was linked from the tutorial...
687
Bob Carpenter
colloquialdo...
Apr 29, 2009 8:28 pm
... What I didn't mention was that it's compiled with 5-grams and then pruned to a minimum count per n-gram of 10. That resulted in a 10MB model that's not...
688
Gustavo Arjones
gustavoarjones
May 10, 2009 5:07 am
I'm interested in sentimental analysis and started few tests of detection. Is it possible do sentimental analysis comparatively? For example: "Java is better...
689
Otis Gospodnetic
otis_gospodn...
May 11, 2009 12:25 am
Hello, My question is similar to Gustavo's (and I closely looked at the sentiment detection tutorial a looong time ago). How well does LingPipe detect...
690
Bob Carpenter
colloquialdo...
May 11, 2009 5:04 pm
... I'm afraid there's nothing built into LingPipe that'll let you do this kind of comparative sentiment extraction out of the box. But there are some...
691
Bob Carpenter
colloquialdo...
May 12, 2009 5:04 pm
We just released a patch for LingPipe 3.8. As usual, it's available from the home page: http://alias-i.com/lingpipe There are only two changes: 1. Bug...
692
Bob Carpenter
colloquialdo...
May 12, 2009 8:45 pm
We received a bug report that the SVD demo program in $LINGPIPE/demos/tutorial/svd/src/Lsi.java throws a null pointer exception as of LingPipe 3.8. I...
693
andrej.kastrin
May 17, 2009 10:18 am
Dear all, could somebody help me with the code below. I want to extract author list from Medline citation. thanks in advance for any suggestions. Cheers,...
694
salinkate
May 17, 2009 7:45 pm
Dear All I've just start learning LingPipe for my project. My project focus on Sentiment Analysis. Now I want to try using new set of movie review from...
695
Bob Carpenter
colloquialdo...
May 18, 2009 5:14 pm
... You're on the right track -- you just need to change the handle() method to handle ciations and then extract the author list from the citation. public void...
696
Bob Carpenter
colloquialdo...
May 18, 2009 5:19 pm
... Starting from our sentiment tutorial, you only need to rewrite the bit that pulls text out of the file-based representations. Alternatively, you can just...
697
andrej.kastrin
May 19, 2009 3:29 pm
Thanks Bob, it works like a charm. Best, Andrej...
698
Bob Carpenter
colloquialdo...
Jun 1, 2009 5:47 pm
Thanks for the bug report: ... ... It should indeed be "length + start". I patched it for the next release. This is what I get for starting the API with...
699
your_69_guy
Jun 9, 2009 8:04 pm
I have a training set of 45K documents for 1000 categories and don't want users of my application to have to wait while the classifier is trained every time...
700
Breck Baldwin
reckb
Jun 9, 2009 10:32 pm
... I have no idea of how Daffodil will deal with java serialization but you can serialize with the AbstractExternalizable class for any of the classifiers...
701
Bob Carpenter
colloquialdo...
Jun 10, 2009 5:49 am
... This will depend on which classifier you use. All of them either implement java.io.Serializable, or they implement com.aliasi.util.Compilable. The...
702
your_69_guy
Jun 12, 2009 2:43 pm
Thanks Bob, the storing of the classifier into a blob field works great. I am having a little trouble reading the object back out of the database though. I...
703
your_69_guy
Jun 12, 2009 3:13 pm
I fiddled with the code some more and got it to work. here is the working code... note : this is extremely fast especially since the blob created from the...
704
Bob Carpenter
colloquialdo...
Jun 12, 2009 5:09 pm
I love it when people solve their own problems before I wake up in the morning! A good way to figure out what you've got serialized is to do this: Object obj =...
705
Bob Carpenter
colloquialdo...
Jul 8, 2009 5:22 pm
Mike just found (and patched) a bug in our scored precision recall evalaution implementation. It was using a TreeSet with a score-based comparator instead of a...
