Moses-support Digest, Vol 153, Issue 2

Send Moses-support mailing list submissions to
moses-support@mit.edu

To subscribe or unsubscribe via the World Wide Web, visit
http://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. 2 Fall research internship position in NLP at Facebook AI
(Juan Miguel Pino)
2. different numbers of runs of mert for same database (rmogla)


----------------------------------------------------------------------

Message: 1
Date: Tue, 2 Jul 2019 17:00:30 +0000
From: Juan Miguel Pino <juancarabina@fb.com>
Subject: [Moses-support] 2 Fall research internship position in NLP at
Facebook AI
To: "moses-support@mit.edu" <moses-support@mit.edu>,
"mt-list@eamt.org" <mt-list@eamt.org>, "corpora@lists.uib.no"
<corpora@lists.uib.no>
Message-ID: <BCA06FEA-87C2-41D1-B646-CE3292B48270@fb.com>
Content-Type: text/plain; charset="utf-8"

[Apologies for cross-posting]

The LATTE (Language And Translation TEchnology) team is part of Facebook AI and is located in Menlo Park, California and Seattle, Washington. We are currently looking for 2 research interns for the Fall. Applicants should be currently pursuing a PhD in NLP and related fields. A strong publication record is highly preferred. The internship lasts 16 weeks, during which we expect the intern to work towards a publication. Possible topics include neural machine translation, comparable corpora mining, representation learning, QA, etc. Please send your CV to Juan Pino (juancarabina@fb.com<mailto:juancarabina@fb.com>) to apply. Note that applications are closing mid July.

Best regards,

Juan

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20190702/d55a47cc/attachment-0001.html

------------------------------

Message: 2
Date: Tue, 2 Jul 2019 23:03:50 +0530
From: rmogla <rmogla01@gmail.com>
Subject: [Moses-support] different numbers of runs of mert for same
database
To: moses-support@mit.edu
Message-ID:
<CAJUS1280RNYzsYVcL92N+1mjJ9OigxW4qmrwy=BBgFU1R1XqMw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

hello,
I am training moses , I ran it twice with the same database using the
baseline system but both the time mert.out file show different numbers of
run.
As in mert.out file:

(8) BEST at 8: 0.118606 0.00894043 0.0616433 0.0270803 -0.00458744
0.0636065 0.0394991 0.121296 -0.0393199 -0.349773 0.0781373 0.00882911
0.0719328 0.00674891 => 0.54342 at Fri...

(7) BEST at 7: 0.042261 0.0543911 0.0644467 0.0409684 -0.114557 0.0567117
0.0807067 0.099067 -0.0280285 -0.277286 0.0593325 0.0104217 0.0663609
-0.00546069 => 0.546516 at Tue...

though the BLEU score of finally trained moses varies by .01,

Please suggest if I am doing something wrong or is it normal to have
various number of mert runs for the same database.

Thanking in advance.
Best Regards
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20190702/3f06933d/attachment-0001.html

------------------------------

_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support


End of Moses-support Digest, Vol 153, Issue 2
*********************************************

Tweet