Moses-support Digest, Vol 106, Issue 4

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. Re: nplm ngram total order in ems (Nikolay Bogoychev)
2. Re: nplm ngram total order in ems (John Joseph Morgan)
3. blm napalm weights name in ems (John Joseph Morgan)


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

Message: 1
Date: Sat, 1 Aug 2015 19:57:26 +0100
From: Nikolay Bogoychev <nheart@gmail.com>
Subject: Re: [Moses-support] nplm ngram total order in ems
To: John Joseph Morgan <johnjosephmorgan@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CAJzPUEzYnnWKipDYCda+1fH9cXuTsuT5fm+sDfNakXfWe3faGQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Hey John,

This is correct. So imagine the situation of order 5 and source window 4:
<s-4><s-3><s-2><s-1><s0><s+1><s+2><s+3><s+4><t-4><t-3><t-2><t-1><t0>
<t0> is aligned to <s0> and your source window is 4: 4 tokens before and
after s0, which results in a 14gram in total.

Cheers,

Nick

On Sat, Aug 1, 2015 at 4:30 PM, John Joseph Morgan <
johnjosephmorgan@gmail.com> wrote:

> I?m trying to run the toy bilingualnplm example with ems.
> The ngram order gets computed in experiment.perl on line 1868.
> The formula is:
> $order + 2 * $source_window + 1
> If $order is 5 and $source_window is 4 this formula gives 14.
> Is this correct?
> It doesn't seem right.
>
> John
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150801/e00177bb/attachment-0001.htm

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

Message: 2
Date: Sat, 1 Aug 2015 15:03:59 -0400
From: John Joseph Morgan <johnjosephmorgan@gmail.com>
Subject: Re: [Moses-support] nplm ngram total order in ems
To: Nikolay Bogoychev <nheart@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID: <DCDCFA5A-DC4C-4F45-9B5E-C7131385179B@gmail.com>
Content-Type: text/plain; charset="utf-8"

Thanks Nick
> On Aug 1, 2015, at 2:57 PM, Nikolay Bogoychev <nheart@gmail.com> wrote:
>
> Hey John,
>
> This is correct. So imagine the situation of order 5 and source window 4:
> <s-4><s-3><s-2><s-1><s0><s+1><s+2><s+3><s+4><t-4><t-3><t-2><t-1><t0>
> <t0> is aligned to <s0> and your source window is 4: 4 tokens before and after s0, which results in a 14gram in total.
>
> Cheers,
>
> Nick
>
> On Sat, Aug 1, 2015 at 4:30 PM, John Joseph Morgan <johnjosephmorgan@gmail.com <mailto:johnjosephmorgan@gmail.com>> wrote:
> I?m trying to run the toy bilingualnplm example with ems.
> The ngram order gets computed in experiment.perl on line 1868.
> The formula is:
> $order + 2 * $source_window + 1
> If $order is 5 and $source_window is 4 this formula gives 14.
> Is this correct?
> It doesn't seem right.
>
> John
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
> http://mailman.mit.edu/mailman/listinfo/moses-support <http://mailman.mit.edu/mailman/listinfo/moses-support>
>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150801/a81f183a/attachment-0001.htm

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

Message: 3
Date: Sun, 2 Aug 2015 10:46:26 -0400
From: John Joseph Morgan <johnjosephmorgan@gmail.com>
Subject: [Moses-support] blm napalm weights name in ems
To: moses-support@mit.edu
Message-ID: <F6033C5B-86ED-4D12-BECD-FC2A99F58F12@gmail.com>
Content-Type: text/plain; charset=utf-8

Hello,
I just wanted to give a heads up that in order to get the ems to run completely with the config.toy.bilinguallm config file I had to make a minor change.
Instead of tuning the config file points to a file called weight_bilinguallm.ini.
I changed the feature name ?BilingualNPLM0? to BLMbilingual-lm?.
I?m running the same setup now with tuning, I?m hoping the feature names get written correctly.
Is there a reason the example weight file has this feature name that I?m missing?
Thanks,
John





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

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


End of Moses-support Digest, Vol 106, Issue 4
*********************************************

Tweet