You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@opennlp.apache.org by Martin Wiesner <ma...@apache.org> on 2024/11/19 17:45:14 UTC

[VOTE] Apache OpenNLP Pre-Trained Models 1.2-rc1

Hi folks,

I've posted a 1st release candidate for the Apache OpenNLP Pre-Trained Model release version 1.2 and it is ready for testing.

Here are the changes compared to version 1.1:

- All models have been trained on the Universal Dependencies corpus version 2.15 using Apache OpenNLP 2.5.0 (and should work with previous OpenNLP versions).
- Training was conducted with 300 iterations instead of 100 which should result in better overall model performance.
- Please note:
	- The Lemmatizer model type was added for all existing and new languages.
	- We now provide models of all four types for the following 9 new languages:
	   -  “Armenian|hy|BSUT”
	   -  “Basque|eu|BDT”
	   -  “Catalan|ca|AnCora”
	   -  “Georgian|ka|GLC”
	   -  “Greek|el|GDT”
	   -  “Kazakh|kk|KTB”
	   -  “Korean|ko|Kaist”
	   -  “Icelandic|is|IcePaHC”
	   -  “Turkish|tr|BOUN”
- Refer to the opennlp-training-eval-logs-1.2-2.5.0.zip file for the individual model training and evaluation logs.
   
In total, OpenNLP now provides pre-trained models for 32 languages.

Models:

https://dist.apache.org/repos/dist/dev/opennlp/models/ud-models-1.2-rc1/

The results of the eval tests for each model are contained in the "opennlp-training-eval-logs-1.2-2.5.0.zip" on dist/dev.

Reminder: The up-2-date KEYS file for signature verification can be
found here: https://dist.apache.org/repos/dist/release/opennlp/KEYS

Please vote on releasing these packages as Apache OpenNLP Pre-Trained Models v1.2.
The vote is open for at least the next 72 hours.

Only votes from OpenNLP PMC are binding, but everyone is welcome to check the release candidate and vote.
The vote passes if at least three binding +1 votes are cast.

Please VOTE

[+1] go ship it
[+0] meh, don't care
[-1] stop, there is a ${showstopper}

Thanks!
Martin

Re: [VOTE] Apache OpenNLP Pre-Trained Models 1.2-rc1

Posted by Bruno Kinoshita <br...@gmail.com>.
+1!

On Tue, 19 Nov 2024 at 18:45, Martin Wiesner <ma...@apache.org> wrote:

> Hi folks,
>
> I've posted a 1st release candidate for the Apache OpenNLP Pre-Trained
> Model release version 1.2 and it is ready for testing.
>
> Here are the changes compared to version 1.1:
>
> - All models have been trained on the Universal Dependencies corpus
> version 2.15 using Apache OpenNLP 2.5.0 (and should work with previous
> OpenNLP versions).
> - Training was conducted with 300 iterations instead of 100 which should
> result in better overall model performance.
> - Please note:
>         - The Lemmatizer model type was added for all existing and new
> languages.
>         - We now provide models of all four types for the following 9 new
> languages:
>            -  “Armenian|hy|BSUT”
>            -  “Basque|eu|BDT”
>            -  “Catalan|ca|AnCora”
>            -  “Georgian|ka|GLC”
>            -  “Greek|el|GDT”
>            -  “Kazakh|kk|KTB”
>            -  “Korean|ko|Kaist”
>            -  “Icelandic|is|IcePaHC”
>            -  “Turkish|tr|BOUN”
> - Refer to the opennlp-training-eval-logs-1.2-2.5.0.zip file for the
> individual model training and evaluation logs.
>
> In total, OpenNLP now provides pre-trained models for 32 languages.
>
> Models:
>
> https://dist.apache.org/repos/dist/dev/opennlp/models/ud-models-1.2-rc1/
>
> The results of the eval tests for each model are contained in the
> "opennlp-training-eval-logs-1.2-2.5.0.zip" on dist/dev.
>
> Reminder: The up-2-date KEYS file for signature verification can be
> found here: https://dist.apache.org/repos/dist/release/opennlp/KEYS
>
> Please vote on releasing these packages as Apache OpenNLP Pre-Trained
> Models v1.2.
> The vote is open for at least the next 72 hours.
>
> Only votes from OpenNLP PMC are binding, but everyone is welcome to check
> the release candidate and vote.
> The vote passes if at least three binding +1 votes are cast.
>
> Please VOTE
>
> [+1] go ship it
> [+0] meh, don't care
> [-1] stop, there is a ${showstopper}
>
> Thanks!
> Martin

Re: [VOTE] Apache OpenNLP Pre-Trained Models 1.2-rc1

Posted by Martin Wiesner <ma...@apache.org>.
Here’s my own +1 (binding)

Cheers,
Martin


> Am 20.11.2024 um 16:12 schrieb Jeff Zemerick <jz...@apache.org>:
> 
> +1
> 
> Richard, thanks for that test script. Should that get checked into the
> repo? Would it be helpful in the future?
> 
> Thanks,
> Jeff
> 
> 
> On Tue, Nov 19, 2024 at 2:08 PM Richard Zowalla <rz...@apache.org> wrote:
> 
>> Hi,
>> 
>> Thanks for preparing.
>> 
>> The „CHANGES“ file contains odd characters. Looks like broken encoding for
>> the quotes to me.
>> 
>> I verified the hashes and signatures using my bulk verification script
>> located here:
>> https://gist.github.com/rzo1/4724f7881ac72e6bb928828f65290cc4
>> 
>> I checked some of the eval logs for details and did some basic usage tests
>> with a few selected models.
>> Overall, it looks good to me.
>> 
>> +1 (binding)
>> 
>> Gruß
>> Richard
>> 
>> 
>> 
>>> Am 19.11.2024 um 18:45 schrieb Martin Wiesner <ma...@apache.org>:
>>> 
>>> Hi folks,
>>> 
>>> I've posted a 1st release candidate for the Apache OpenNLP Pre-Trained
>> Model release version 1.2 and it is ready for testing.
>>> 
>>> Here are the changes compared to version 1.1:
>>> 
>>> - All models have been trained on the Universal Dependencies corpus
>> version 2.15 using Apache OpenNLP 2.5.0 (and should work with previous
>> OpenNLP versions).
>>> - Training was conducted with 300 iterations instead of 100 which should
>> result in better overall model performance.
>>> - Please note:
>>>      - The Lemmatizer model type was added for all existing and new
>> languages.
>>>      - We now provide models of all four types for the following 9 new
>> languages:
>>>         -  “Armenian|hy|BSUT”
>>>         -  “Basque|eu|BDT”
>>>         -  “Catalan|ca|AnCora”
>>>         -  “Georgian|ka|GLC”
>>>         -  “Greek|el|GDT”
>>>         -  “Kazakh|kk|KTB”
>>>         -  “Korean|ko|Kaist”
>>>         -  “Icelandic|is|IcePaHC”
>>>         -  “Turkish|tr|BOUN”
>>> - Refer to the opennlp-training-eval-logs-1.2-2.5.0.zip file for the
>> individual model training and evaluation logs.
>>> 
>>> In total, OpenNLP now provides pre-trained models for 32 languages.
>>> 
>>> Models:
>>> 
>>> https://dist.apache.org/repos/dist/dev/opennlp/models/ud-models-1.2-rc1/
>>> 
>>> The results of the eval tests for each model are contained in the
>> "opennlp-training-eval-logs-1.2-2.5.0.zip" on dist/dev.
>>> 
>>> Reminder: The up-2-date KEYS file for signature verification can be
>>> found here: https://dist.apache.org/repos/dist/release/opennlp/KEYS
>>> 
>>> Please vote on releasing these packages as Apache OpenNLP Pre-Trained
>> Models v1.2.
>>> The vote is open for at least the next 72 hours.
>>> 
>>> Only votes from OpenNLP PMC are binding, but everyone is welcome to
>> check the release candidate and vote.
>>> The vote passes if at least three binding +1 votes are cast.
>>> 
>>> Please VOTE
>>> 
>>> [+1] go ship it
>>> [+0] meh, don't care
>>> [-1] stop, there is a ${showstopper}
>>> 
>>> Thanks!
>>> Martin
>> 
>> 

--
Colorful Bytes GmbH
Blumenstraße 20
74906 Bad Rappenau
Sitz: Bad Rappenau
Registergericht Stuttgart
HRB 758952

Geschäftsführung:
Dr. Monika Pobiruchin
Martin Wiesner
Dr. Richard Zowalla
Daniel Zsebedits
Website
E-Mail
Telefon
© 2024 Colorful Bytes GmbH

Re: [VOTE] Apache OpenNLP Pre-Trained Models 1.2-rc1

Posted by Jeff Zemerick <jz...@apache.org>.
+1

Richard, thanks for that test script. Should that get checked into the
repo? Would it be helpful in the future?

Thanks,
Jeff


On Tue, Nov 19, 2024 at 2:08 PM Richard Zowalla <rz...@apache.org> wrote:

> Hi,
>
> Thanks for preparing.
>
> The „CHANGES“ file contains odd characters. Looks like broken encoding for
> the quotes to me.
>
> I verified the hashes and signatures using my bulk verification script
> located here:
> https://gist.github.com/rzo1/4724f7881ac72e6bb928828f65290cc4
>
> I checked some of the eval logs for details and did some basic usage tests
> with a few selected models.
> Overall, it looks good to me.
>
> +1 (binding)
>
> Gruß
> Richard
>
>
>
> > Am 19.11.2024 um 18:45 schrieb Martin Wiesner <ma...@apache.org>:
> >
> > Hi folks,
> >
> > I've posted a 1st release candidate for the Apache OpenNLP Pre-Trained
> Model release version 1.2 and it is ready for testing.
> >
> > Here are the changes compared to version 1.1:
> >
> > - All models have been trained on the Universal Dependencies corpus
> version 2.15 using Apache OpenNLP 2.5.0 (and should work with previous
> OpenNLP versions).
> > - Training was conducted with 300 iterations instead of 100 which should
> result in better overall model performance.
> > - Please note:
> >       - The Lemmatizer model type was added for all existing and new
> languages.
> >       - We now provide models of all four types for the following 9 new
> languages:
> >          -  “Armenian|hy|BSUT”
> >          -  “Basque|eu|BDT”
> >          -  “Catalan|ca|AnCora”
> >          -  “Georgian|ka|GLC”
> >          -  “Greek|el|GDT”
> >          -  “Kazakh|kk|KTB”
> >          -  “Korean|ko|Kaist”
> >          -  “Icelandic|is|IcePaHC”
> >          -  “Turkish|tr|BOUN”
> > - Refer to the opennlp-training-eval-logs-1.2-2.5.0.zip file for the
> individual model training and evaluation logs.
> >
> > In total, OpenNLP now provides pre-trained models for 32 languages.
> >
> > Models:
> >
> > https://dist.apache.org/repos/dist/dev/opennlp/models/ud-models-1.2-rc1/
> >
> > The results of the eval tests for each model are contained in the
> "opennlp-training-eval-logs-1.2-2.5.0.zip" on dist/dev.
> >
> > Reminder: The up-2-date KEYS file for signature verification can be
> > found here: https://dist.apache.org/repos/dist/release/opennlp/KEYS
> >
> > Please vote on releasing these packages as Apache OpenNLP Pre-Trained
> Models v1.2.
> > The vote is open for at least the next 72 hours.
> >
> > Only votes from OpenNLP PMC are binding, but everyone is welcome to
> check the release candidate and vote.
> > The vote passes if at least three binding +1 votes are cast.
> >
> > Please VOTE
> >
> > [+1] go ship it
> > [+0] meh, don't care
> > [-1] stop, there is a ${showstopper}
> >
> > Thanks!
> > Martin
>
>

Re: [VOTE] Apache OpenNLP Pre-Trained Models 1.2-rc1

Posted by Richard Zowalla <rz...@apache.org>.
Hi,

Thanks for preparing.

The „CHANGES“ file contains odd characters. Looks like broken encoding for the quotes to me.

I verified the hashes and signatures using my bulk verification script located here: https://gist.github.com/rzo1/4724f7881ac72e6bb928828f65290cc4

I checked some of the eval logs for details and did some basic usage tests with a few selected models.
Overall, it looks good to me.

+1 (binding)

Gruß
Richard



> Am 19.11.2024 um 18:45 schrieb Martin Wiesner <ma...@apache.org>:
> 
> Hi folks,
> 
> I've posted a 1st release candidate for the Apache OpenNLP Pre-Trained Model release version 1.2 and it is ready for testing.
> 
> Here are the changes compared to version 1.1:
> 
> - All models have been trained on the Universal Dependencies corpus version 2.15 using Apache OpenNLP 2.5.0 (and should work with previous OpenNLP versions).
> - Training was conducted with 300 iterations instead of 100 which should result in better overall model performance.
> - Please note:
> 	- The Lemmatizer model type was added for all existing and new languages.
> 	- We now provide models of all four types for the following 9 new languages:
> 	   -  “Armenian|hy|BSUT”
> 	   -  “Basque|eu|BDT”
> 	   -  “Catalan|ca|AnCora”
> 	   -  “Georgian|ka|GLC”
> 	   -  “Greek|el|GDT”
> 	   -  “Kazakh|kk|KTB”
> 	   -  “Korean|ko|Kaist”
> 	   -  “Icelandic|is|IcePaHC”
> 	   -  “Turkish|tr|BOUN”
> - Refer to the opennlp-training-eval-logs-1.2-2.5.0.zip file for the individual model training and evaluation logs.
> 
> In total, OpenNLP now provides pre-trained models for 32 languages.
> 
> Models:
> 
> https://dist.apache.org/repos/dist/dev/opennlp/models/ud-models-1.2-rc1/
> 
> The results of the eval tests for each model are contained in the "opennlp-training-eval-logs-1.2-2.5.0.zip" on dist/dev.
> 
> Reminder: The up-2-date KEYS file for signature verification can be
> found here: https://dist.apache.org/repos/dist/release/opennlp/KEYS
> 
> Please vote on releasing these packages as Apache OpenNLP Pre-Trained Models v1.2.
> The vote is open for at least the next 72 hours.
> 
> Only votes from OpenNLP PMC are binding, but everyone is welcome to check the release candidate and vote.
> The vote passes if at least three binding +1 votes are cast.
> 
> Please VOTE
> 
> [+1] go ship it
> [+0] meh, don't care
> [-1] stop, there is a ${showstopper}
> 
> Thanks!
> Martin