[GitHub] opennlp pull request #112: OPENNLP-904

GitHub user ragerri opened a pull request: https://github.com/apache/opennlp/pull/112 OPENNLP-904 Lemmatizer Interface changed to harmonize use across Dictionary, Morfologik and LemmatizerME lemmatizers. You can merge this pull request into a Git repository by running: $ git p

[GitHub] opennlp pull request #111: OPENNLP-975: Add format support for CoNLL-U forma...

Github user asfgit closed the pull request at: https://github.com/apache/opennlp/pull/111 --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is ena

Re: Name Finder trainer default settings

Hi Jörn, I think the best entity recognition systems use CRF’s. At some point we might want to consider adding them. As you know, ME classifiers suffer from label bias problem (see Lafferty et. al.) CRF’s d

Re: Name Finder trainer default settings

I have good results with perceptron, but +1 for CRF 2017-02-07 15:42 GMT+01:00 Russ, Daniel (NIH/CIT) [E] : > Hi Jörn, > > > >I think the best entity recognition systems use CRF’s. At some point > we might want to consider adding them. As you know, ME classifiers suffer > from label bias pr

Re: Name Finder trainer default settings

It would be interesting to compare the results of OpenNLP’s perceptron trained models, GIS trained models, and a vanilla CRF implementation (i.e. not specifically trained for a task). We can make a better decision on if we should spend the effort to implement a CRF. Every once in a while we se

Re: Name Finder trainer default settings

We actually can train a CRF from Mallet with the existing infrastructure, and the code should still work (maybe there are minor issues, who knows). I tried that but just couldn't get better results. We should maybe try to get this code (mallet-addon) into a good shape again and then see what the is

Re: Name Finder trainer default settings

Hi Daniel, Previous publications suggest features are more important than learning methods. Before last year, the trend seemed to go towards CRFs, nowadays, it goes towards deep learning (LSTM, CNN, RNN, etc. and so on). However, if we do a very quick review of English results for CoNLL 2003 (the

Re: Name Finder trainer default settings

Very interesting… the difference is a lot less than I thought. 1. Ratinov and Roth (2009): 90.57 F1 Perceptron 2. Passos et al. (2009): 90.90 F1 CRF Seeing this numbers get my +1 on Jörn’s original comment. I was under the impressions that CRFs did a lot better (Myth busted). I comp

[GitHub] opennlp pull request #113: OPENNLP-964: Ignore LICENSE, NOTICE and README fi...

GitHub user kottmann opened a pull request: https://github.com/apache/opennlp/pull/113 OPENNLP-964: Ignore LICENSE, NOTICE and README files in the model You can merge this pull request into a Git repository by running: $ git pull https://github.com/kottmann/opennlp OPENNLP-964

[GitHub] opennlp pull request #114: [WIP] OPENNLP-176: Switch language codes to ISO-6...

GitHub user kottmann opened a pull request: https://github.com/apache/opennlp/pull/114 [WIP] OPENNLP-176: Switch language codes to ISO-639-3 You can merge this pull request into a Git repository by running: $ git pull https://github.com/kottmann/opennlp OPENNLP-176 Alternativ

[GitHub] opennlp pull request #115: NoJira: Run coveralls:report after build

GitHub user kottmann opened a pull request: https://github.com/apache/opennlp/pull/115 NoJira: Run coveralls:report after build You can merge this pull request into a Git repository by running: $ git pull https://github.com/kottmann/opennlp coveralls_test Alternatively you ca

[GitHub] opennlp pull request #110: OpenNLP-977 Remove deprecated map methods

Github user danielruss closed the pull request at: https://github.com/apache/opennlp/pull/110 --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is

[GitHub] opennlp pull request #115: NoJira: Run coveralls:report after build

Github user asfgit closed the pull request at: https://github.com/apache/opennlp/pull/115 --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is ena

[GitHub] opennlp pull request #116: NoJira: Fix Jacoco plugin failure for opennlp-too...

GitHub user smarthi opened a pull request: https://github.com/apache/opennlp/pull/116 NoJira: Fix Jacoco plugin failure for opennlp-tools You can merge this pull request into a Git repository by running: $ git pull https://github.com/smarthi/opennlp sundry Alternatively you c

[GitHub] opennlp pull request #116: NoJira: Fix Jacoco plugin failure for opennlp-too...

Github user asfgit closed the pull request at: https://github.com/apache/opennlp/pull/116 --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is ena