Send Moses-support mailing list submissions to
moses-support@mit.edu
To subscribe or unsubscribe via the World Wide Web, visit
https://mailman.mit.edu/mailman/listinfo/moses-support
or, via email, send a message with subject or body 'help' to
moses-support-request@mit.edu
You can reach the person managing the list at
moses-support-owner@mit.edu
When replying, please edit your Subject line so it is more specific
than "Re: Contents of Moses-support digest..."
Today's Topics:
1. Re: Pure-python decoder for Moses? (Rachel Bawden)
----------------------------------------------------------------------
Message: 1
Date: Wed, 26 Jan 2022 15:08:48 +0100
From: Rachel Bawden <rachel.a.bawden@gmail.com>
To: Hieu Hoang <hieuhoang@gmail.com>
Cc: Lane Schwartz <dowobeha@gmail.com>, liling tan
<alvations@gmail.com>, moses-support <Moses-support@mit.edu>
Subject: Re: [Moses-support] Pure-python decoder for Moses?
Message-ID: <7B627E28-C5EB-4991-8267-FBEEF57D830C@gmail.com>
Content-Type: text/plain; charset="utf-8"
Thank you both! This is really helpful.
The NLTK package looks like a good starting point. It doesn?t seem to have all Moses functionalities - for example using tuned weights, but I?ll see if I can find time to adapt it :-D
Thanks again,
Rachel
> On 24 Jan 2022, at 18:52, Hieu Hoang <hieuhoang@gmail.com> wrote:
>
> NLTK had something but not sure how good it is
> https://www.nltk.org/_modules/nltk/translate/phrase_based.html <https://www.nltk.org/_modules/nltk/translate/phrase_based.html>
> Liling may know more about it
>
> Hieu Hoang
> http://statmt.org/hieu <http://statmt.org/hieu>
>
> On Mon, 24 Jan 2022 at 09:50, Lane Schwartz <dowobeha@gmail.com <mailto:dowobeha@gmail.com>> wrote:
> Pretty sure the answer is no. David Chiang had a Python-based system, but it was hierarchical phrase-based.
>
>
>
> On Mon, Jan 24, 2022 at 8:50 AM Rachel Bawden <rachel.a.bawden@gmail.com <mailto:rachel.a.bawden@gmail.com>> wrote:
> Hello,
>
> Are there currently any pure-python implementations of mosesdecoder? I am looking to distribute and run pre-trained models (so no tuning) without having to compile Moses, even though decoding will inevitably be less efficient.
>
> Thank you very much in advance,
> All the best,
>
> Rachel
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
> https://mailman.mit.edu/mailman/listinfo/moses-support <https://mailman.mit.edu/mailman/listinfo/moses-support>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
> https://mailman.mit.edu/mailman/listinfo/moses-support <https://mailman.mit.edu/mailman/listinfo/moses-support>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.mit.edu/mailman/private/moses-support/attachments/20220126/77eaf7fb/attachment-0001.htm>
------------------------------
Subject: Digest Footer
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
https://mailman.mit.edu/mailman/listinfo/moses-support
------------------------------
End of Moses-support Digest, Vol 182, Issue 6
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 182, Issue 6"
Post a Comment