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. detecting if a translation is machine or human translation
(Ryan Coughlin)
2. Re: detecting if a translation is machine or human
translation (Philipp Koehn)
3. Re: detecting if a translation is machine or human
translation (Mathias M?ller)
4. Re: detecting if a translation is machine or human
translation (Kenneth Heafield)
----------------------------------------------------------------------
Message: 1
Date: Fri, 6 Apr 2018 09:14:23 +0700
From: Ryan Coughlin <ryan.c@sis.edu>
Subject: [Moses-support] detecting if a translation is machine or
human translation
To: moses-support@mit.edu
Message-ID:
<CA+qMsK5SxvhU+bM6kbHqWd+su18pm5HT=bRxg4dzAM6yzzCPSQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Hi all,
Hope you all had a happy Easter and are having a good spring (or autumn).
One of the admins from Open Subtitles asked me if I knew of a way to
detect if a translation was machine or machine or human translation. The
website seems to have a lot of submissions that are simply Google
translated, and they're looking for a script to flag these submissions. Do
you have any ideas how they might go about this?
I was thinking of running the SL against a few of the popular SMT
programs, and seeing if the BLEU scores were too similar, but the method
seems too random and computationally heavy. I'd appreciate any thoughts.
thank you,
Ryan
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20180405/4a7c858c/attachment-0001.html
------------------------------
Message: 2
Date: Thu, 5 Apr 2018 22:47:25 -0400
From: Philipp Koehn <phi@jhu.edu>
Subject: Re: [Moses-support] detecting if a translation is machine or
human translation
To: Ryan Coughlin <ryan.c@sis.edu>
Cc: Moses Support <moses-support@mit.edu>
Message-ID:
<CAAFADDAZR9eDADf3_njUxWr5LX9PrUGO2aDm4ZSj6pgNhm-DNw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Hi,
there has been some work on this.
See Section 2.4 in
http://www.aclweb.org/anthology/W16-2347
for some references.
The main ideas are to look for properties of machine translation - i.e.,
that is very literal and may have certain systematic errors.
This is a hard problem, though.
-phi
On Thu, Apr 5, 2018 at 10:14 PM, Ryan Coughlin <ryan.c@sis.edu> wrote:
> Hi all,
>
> Hope you all had a happy Easter and are having a good spring (or autumn).
>
> One of the admins from Open Subtitles asked me if I knew of a way to
> detect if a translation was machine or machine or human translation. The
> website seems to have a lot of submissions that are simply Google
> translated, and they're looking for a script to flag these submissions. Do
> you have any ideas how they might go about this?
>
> I was thinking of running the SL against a few of the popular SMT
> programs, and seeing if the BLEU scores were too similar, but the method
> seems too random and computationally heavy. I'd appreciate any thoughts.
>
> thank you,
> Ryan
>
> _______________________________________________
> 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/20180405/885e27c0/attachment-0001.html
------------------------------
Message: 3
Date: Fri, 6 Apr 2018 10:14:21 +0200
From: Mathias M?ller <mmueller@ifi.uzh.ch>
Subject: Re: [Moses-support] detecting if a translation is machine or
human translation
To: Ryan Coughlin <ryan.c@sis.edu>
Cc: moses-support@mit.edu
Message-ID: <491C27AE-E4C1-4B57-887B-851B1D50BF38@ifi.uzh.ch>
Content-Type: text/plain; charset="us-ascii"
Hi Ryan
My two cents:
First of all, a way of detecting Google-translated text might be to take the original text and run it through Google Translate (if they have access to an API, I mean). Then see if an alleged machine translated-text is similar to this.
Here is another pointer to literature for you:
http://www.aclweb.org/anthology/P14-2048 <http://www.aclweb.org/anthology/P14-2048>
Regards
Mathias
> On 6 Apr 2018, at 04:14, Ryan Coughlin <ryan.c@sis.edu> wrote:
>
> Hi all,
>
> Hope you all had a happy Easter and are having a good spring (or autumn).
>
> One of the admins from Open Subtitles asked me if I knew of a way to detect if a translation was machine or machine or human translation. The website seems to have a lot of submissions that are simply Google translated, and they're looking for a script to flag these submissions. Do you have any ideas how they might go about this?
>
> I was thinking of running the SL against a few of the popular SMT programs, and seeing if the BLEU scores were too similar, but the method seems too random and computationally heavy. I'd appreciate any thoughts.
>
> thank you,
> Ryan
> _______________________________________________
> 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/20180406/a947b77a/attachment-0001.html
------------------------------
Message: 4
Date: Fri, 6 Apr 2018 09:30:28 +0100
From: Kenneth Heafield <moses@kheafield.com>
Subject: Re: [Moses-support] detecting if a translation is machine or
human translation
To: moses-support@mit.edu
Message-ID: <8e09019a-bd1b-3465-fd8f-a3cdc4b09191@kheafield.com>
Content-Type: text/plain; charset=windows-1252
Google watermarked their translation output:
https://research.google.com/pubs/archive/37162.pdf
Would be good to check if they're still doing this with neural systems.
On 04/06/2018 09:14 AM, Mathias M?ller wrote:
> Hi Ryan
>
> My two cents:
>
> First of all, a way of detecting Google-translated text might be to take
> the original text and run it through Google Translate (if they have
> access to an API, I mean). Then see if an alleged machine
> translated-text is similar to this.
>
> Here is another pointer to literature for you:
>
> http://www.aclweb.org/anthology/P14-2048
>
> Regards
> Mathias
>
>> On 6 Apr 2018, at 04:14, Ryan Coughlin <ryan.c@sis.edu
>> <mailto:ryan.c@sis.edu>> wrote:
>>
>> Hi all,
>>
>> ? Hope you all had a happy Easter and are having a good spring (or
>> autumn).
>>
>> ? One of the admins from Open Subtitles asked me if I knew of a way to
>> detect if a translation was machine or machine or human translation.
>> The website seems to have a lot of submissions that are simply Google
>> translated, and they're looking for a script to flag these
>> submissions. Do you have any ideas how they might go about this?
>>
>> ? I was thinking of running the SL against a few of the popular SMT
>> programs, and seeing if the BLEU scores were too similar, but the
>> method seems too random and computationally heavy. I'd appreciate any
>> thoughts.
>>
>> thank you,
>> Ryan
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 138, Issue 2
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 138, Issue 2"
Post a Comment