Home » Uncategories » Moses-support Digest, Vol 90, Issue 33

Moses-support Digest, Vol 90, Issue 33

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: cube pruning and growing (Barry Haddow)
2. Re: cube pruning and growing (Kenneth Heafield)
3. Mosesserver Error- Mosesdecoder.V211 (Lakshya)


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

Message: 1
Date: Fri, 11 Apr 2014 17:36:47 +0100
From: Barry Haddow <bhaddow@staffmail.ed.ac.uk>
Subject: Re: [Moses-support] cube pruning and growing
To: David Mrva <davidm@cantabresearch.com>, moses-support@mit.edu
Message-ID: <53481A1F.1020908@staffmail.ed.ac.uk>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

Hi David

Cube pruning works for moses and moses_chart. Cubr growing was
implemented in a branch (for moses_chart, afaik) and has never been
merged in , it must have been just stubbed out in the master branch,

cheers - Barry

On 11/04/14 16:17, David Mrva wrote:
> Hi all,
>
> Is cube pruning (see http://www.aclweb.org/anthology/P/P07/P07-1019.pdf)
> supported by moses out of the box?
>
> The search-algortihm option's description suggests that it is:
> -search-algorithm: Which search algorithm to use. 0=normal stack, 1=cube
> pruning, 2=cube growing, 4=stack with batched lm requests (default = 0)
>
> and despite the SearchAlgorithm enum in moses/TypeDef.h having a slot
> for it:
> enum SearchAlgorithm {
> ...
> ,CubeGrowing = 2
> ...
> };
>
> the Search::CreateSearch() method does not seem to support this choice:
> ...
> case CubeGrowing:
> return NULL;
> ....
>
> Using "-search-algorithm 2" results in an instant seg fault. I use moses
> checked out of github.
>
> Many thanks,
> David
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>


--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.



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

Message: 2
Date: Fri, 11 Apr 2014 09:42:58 -0700
From: Kenneth Heafield <moses@kheafield.com>
Subject: Re: [Moses-support] cube pruning and growing
To: moses-support@mit.edu
Message-ID: <53481B92.1080307@kheafield.com>
Content-Type: text/plain; charset=ISO-8859-1

And at a more practical level, you're looking for -search-algorithm 1
for phrase-based cube pruning. Somebody conflated search algorithm with
search space and that distinction survives today.

Kenneth

On 04/11/14 09:36, Barry Haddow wrote:
> Hi David
>
> Cube pruning works for moses and moses_chart. Cubr growing was
> implemented in a branch (for moses_chart, afaik) and has never been
> merged in , it must have been just stubbed out in the master branch,
>
> cheers - Barry
>
> On 11/04/14 16:17, David Mrva wrote:
>> Hi all,
>>
>> Is cube pruning (see http://www.aclweb.org/anthology/P/P07/P07-1019.pdf)
>> supported by moses out of the box?
>>
>> The search-algortihm option's description suggests that it is:
>> -search-algorithm: Which search algorithm to use. 0=normal stack, 1=cube
>> pruning, 2=cube growing, 4=stack with batched lm requests (default = 0)
>>
>> and despite the SearchAlgorithm enum in moses/TypeDef.h having a slot
>> for it:
>> enum SearchAlgorithm {
>> ...
>> ,CubeGrowing = 2
>> ...
>> };
>>
>> the Search::CreateSearch() method does not seem to support this choice:
>> ...
>> case CubeGrowing:
>> return NULL;
>> ....
>>
>> Using "-search-algorithm 2" results in an instant seg fault. I use moses
>> checked out of github.
>>
>> Many thanks,
>> David
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>
>


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

Message: 3
Date: Fri, 11 Apr 2014 22:32:09 +0530
From: Lakshya <elekshman@gmail.com>
Subject: [Moses-support] Mosesserver Error- Mosesdecoder.V211
To: Barry Haddow <bhaddow@staffmail.ed.ac.uk>
Cc: moses-support@mit.edu
Message-ID:
<CANiOhcN62UNE19LkNm-ApguHXabX=1KfiZvNr459dKx8sijtug@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

Thanks Barry for your help.

Now the moseserver is responding to the request. But it ended up in one
another error when I am trying to retrieve values through "nbest" keyword
from moseserver. Below is the xmlrpc trace.

XML-RPC CALL:

<?xml version="1.0"
encoding="UTF-8"?><methodCall><methodName>translate</methodName><params><param><value><struct><member><name>topt</name><value>true</value></member><member><name>text</name><value>\xff\xff\xff\xff\xff\xff
\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff,
\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff
\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff,
\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff
\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff
\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff
\xff\xff\xff\xff\xff\xff\xff\xff\xff.</value></member><member><name>nbest</name><value>true</value></member><member><name>align</name><value>true</value></member><member><name>report-all-factors</name><value>true</value></member><member><name>sg</name><value>true</value></member></struct></value></param></params></methodCall>

Input: He was busy with his works.
XML-RPC RESPONSE:

<?xml version="1.0" encoding="UTF-8"?>\r\n
<methodResponse>\r\n
<fault>\r\n
<value><struct>\r\n
<member><name>faultCode</name>\r\n
<value><i4>-500</i4></value></member>\r\n
<member><name>faultString</name>\r\n
<value><string>Unexpected error executing code for particular method,
detected by Xmlrpc-c method registry code. Method did not fail; rather, it
did not complete at all. Not integer type. See type()
method</string></value></member>\r\n
</struct></value>\r\n
</fault>\r\n
</methodResponse>\r\n


could you please help me how can i retrieve nbest values..

Expecting your reply

Lakshya


On Thu, Apr 10, 2014 at 10:58 PM, Barry Haddow
<bhaddow@staffmail.ed.ac.uk>wrote:

> Hi Lakysha
>
> There has been very little change in the moses server.
>
> Try running the following before you launch moses server
> export XMLRPC_TRACE_XML=1
> and you should get a dump of the xmlrpc messages. This may help you debug
> the problem,
>
> cheers - Barry
>
>
> On 09/04/14 20:47, Lakshya wrote:
>
>> Hi Everybody,
>>
>> I am also facing problem with Mosesdecoder.v211 moseserver. I have
>> compiled the moseserver with out any error and the moseserver is
>> listenening to the port also. But when a translation request is going from
>> the interface, there is no responds from the mosesserver.
>>
>> I am getting the folowing exception.. org.apache.xmlrpc.XmlRpcException:
>> Failed to read server's response: Connection refused
>>
>> Is there any difference in the moseswerver connection of Mosesdecoder
>> Release 1.0 and Mosesdecoder.V211. ?
>>
>>
>>
>> could anybody please clarify these doubts and how can I establish the
>> moseserver connection..
>>
>>
>> Regards
>> Lakshya
>>
>> Message: 1
>> Date: Mon, 7 Apr 2014 18:25:35 +0100
>> From: kamel nebhi <k.nebhi@sheffield.ac.uk <mailto:k.nebhi@sheffield.ac.
>> uk>>
>>
>> Subject: [Moses-support] moses server segmentation fault (core dumped)
>> To: moses-support <moses-support@mit.edu <mailto:moses-support@mit.edu>>
>> Message-ID:
>> <CAG66Y3c2UFq5+
>> 2w4eV00RrwVrMWTtVxpQ7=jgXFwNG+aFnRjCA@mail.gmail.com <mailto:
>> jgXFwNG%2BaFnRjCA@mail.gmail.com>>
>>
>> Content-Type: text/plain; charset="utf-8"
>>
>> Hi,
>>
>> I try to install mosesserver on localhost. I have installed xml-rpc and
>> rebuild moses with no problem.
>>
>> Next i use this command to run the server : *~/mosesdecoder/bin/
>> mosesserver
>> -f working/model/moses.ini --server-port 8999*
>>
>> But it failed with this message :
>>
>> Defined parameters (per moses.ini or switch):
>> config: /home/kamelnebhi/recaser/training/moses.ini
>> distortion-limit: 6
>> feature: UnknownWordPenalty WordPenalty PhrasePenalty
>> PhraseDictionaryMemory name=TranslationModel0 table-limit=20
>> num-features=4
>> path=/home/kamelnebhi/recaser/training/phrase-table.gz input-factor=0
>> output-factor=0 Distortion KENLM lazyken=0 name=LM0 factor=0
>> path=/home/kamelnebhi/recaser/training//cased.srilm.gz order=3
>> input-factors: 0
>> mapping: 0 T 0
>> weight: UnknownWordPenalty0= 1 WordPenalty0= -1 PhrasePenalty0= 0.2
>> TranslationModel0= 0.2 0.2 0.2 0.2 Distortion0= 0.3 LM0= 0.5
>> /home/kamelnebhi/mosesdecoder/bin
>> line=UnknownWordPenalty
>> FeatureFunction: UnknownWordPenalty0 start: 0 end: 0
>> line=WordPenalty
>> FeatureFunction: WordPenalty0 start: 1 end: 1
>> line=PhrasePenalty
>> FeatureFunction: PhrasePenalty0 start: 2 end: 2
>> line=PhraseDictionaryMemory name=TranslationModel0 table-limit=20
>> num-features=4 path=/home/kamelnebhi/recaser/training/phrase-table.gz
>> input-factor=0 output-factor=0
>> FeatureFunction: TranslationModel0 start: 3 end: 6
>> line=Distortion
>> FeatureFunction: Distortion0 start: 7 end: 7
>> line=KENLM lazyken=0 name=LM0 factor=0
>> path=/home/kamelnebhi/recaser/training//cased.srilm.gz order=3
>> FeatureFunction: LM0 start: 8 end: 8
>> Loading the LM will be faster if you build a binary file.
>> Reading /home/kamelnebhi/recaser/training//cased.srilm.gz
>> ----5---10---15---20---25---30---35---40---45---50---55---
>> 60---65---70---75---80---85---90---95--100
>> *The ARPA file is missing <unk>. Substituting log10 probability -100.
>> ************************************************************
>> ***************************************
>> Loading UnknownWordPenalty0
>> Loading WordPenalty0
>> Loading PhrasePenalty0
>> Loading Distortion0
>> Loading LM0
>> Loading TranslationModel0
>> Start loading text SCFG phrase table. Moses format : [3.69361] seconds
>> Reading /home/kamelnebhi/recaser/training/phrase-table.gz
>> ----5---10---15---20---25---30---35---40---45---50---55---
>> 60---65---70---75---80---85---90---95--100
>> ************************************************************
>> ****************************************
>> Erreur de segmentation (core dumped)
>> root@kamelnebhi-MacBookPro:/home/kamelnebhi#
>> /home/kamelnebhi/mosesdecoder/bin/mosesserver -f
>> /home/kamelnebhi/recaser/training/moses.ini --server-port 80
>> Defined parameters (per moses.ini or switch):
>> config: /home/kamelnebhi/recaser/training/moses.ini
>> distortion-limit: 6
>> feature: UnknownWordPenalty WordPenalty PhrasePenalty
>> PhraseDictionaryMemory name=TranslationModel0 table-limit=20
>> num-features=4
>> path=/home/kamelnebhi/recaser/training/phrase-table.gz input-factor=0
>> output-factor=0 Distortion KENLM lazyken=0 name=LM0 factor=0
>> path=/home/kamelnebhi/recaser/training//cased.srilm.gz order=3
>> input-factors: 0
>> mapping: 0 T 0
>> weight: UnknownWordPenalty0= 1 WordPenalty0= -1 PhrasePenalty0= 0.2
>> TranslationModel0= 0.2 0.2 0.2 0.2 Distortion0= 0.3 LM0= 0.5
>> /home/kamelnebhi/mosesdecoder/bin
>> line=UnknownWordPenalty
>> FeatureFunction: UnknownWordPenalty0 start: 0 end: 0
>> line=WordPenalty
>> FeatureFunction: WordPenalty0 start: 1 end: 1
>> line=PhrasePenalty
>> FeatureFunction: PhrasePenalty0 start: 2 end: 2
>> line=PhraseDictionaryMemory name=TranslationModel0 table-limit=20
>> num-features=4 path=/home/kamelnebhi/recaser/training/phrase-table.gz
>> input-factor=0 output-factor=0
>> FeatureFunction: TranslationModel0 start: 3 end: 6
>> line=Distortion
>> FeatureFunction: Distortion0 start: 7 end: 7
>> line=KENLM lazyken=0 name=LM0 factor=0
>> path=/home/kamelnebhi/recaser/training//cased.srilm.gz order=3
>> FeatureFunction: LM0 start: 8 end: 8
>> Loading the LM will be faster if you build a binary file.
>> Reading /home/kamelnebhi/recaser/training//cased.srilm.gz
>> ----5---10---15---20---25---30---35---40---45---50---55---
>> 60---65---70---75---80---85---90---95--100
>> *The ARPA file is missing <unk>. Substituting log10 probability -100.
>> ************************************************************
>> ***************************************
>> Loading UnknownWordPenalty0
>> Loading WordPenalty0
>> Loading PhrasePenalty0
>> Loading Distortion0
>> Loading LM0
>> Loading TranslationModel0
>> Start loading text SCFG phrase table. Moses format : [3.69152] seconds
>> Reading /home/kamelnebhi/recaser/training/phrase-table.gz
>> ----5---10---15---20---25---30---35---40---45---50---55---
>> 60---65---70---75---80---85---90---95--100
>> ************************************************************
>> ****************************************
>> Segmentation fault (core dumped)
>>
>> *Thanks for your help*
>> -------------- next part --------------
>> An HTML attachment was scrubbed...
>> URL: http://mailman.mit.edu/mailman/private/moses-support/
>> attachments/20140407/82302fab/attachment-0001.htm
>>
>> ------------------------------
>>
>> ---------- Forwarded message ----------
>> From: <moses-support-request@mit.edu <mailto:moses-support-request@
>> mit.edu>>
>> Date: Tue, Apr 8, 2014 at 3:57 AM
>> Subject: Moses-support Digest, Vol 90, Issue 19
>> To: moses-support@mit.edu <mailto:moses-support@mit.edu>
>>
>>
>> Send Moses-support mailing list submissions to
>> moses-support@mit.edu <mailto: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 <mailto:moses-support-request@mit.edu>
>>
>>
>> You can reach the person managing the list at
>> moses-support-owner@mit.edu <mailto: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. moses server segmentation fault (core dumped) (kamel nebhi)
>> 2. Re: Monolingual Word alignment (Philipp Koehn)
>> 3. Call for Participation: Automatic and Manual Metrics for
>> Operational Translation Evaluation (Lucia Specia)
>>
>>
>> ----------------------------------------------------------------------
>>
>> Message: 1
>> Date: Mon, 7 Apr 2014 18:25:35 +0100
>> From: kamel nebhi <k.nebhi@sheffield.ac.uk <mailto:k.nebhi@sheffield.ac.
>> uk>>
>>
>> Subject: [Moses-support] moses server segmentation fault (core dumped)
>> To: moses-support <moses-support@mit.edu <mailto:moses-support@mit.edu>>
>> Message-ID:
>> <CAG66Y3c2UFq5+2w4eV00RrwVrMWTtVxpQ7=jgXFwNG+
>> aFnRjCA@mail.gmail.com <mailto:jgXFwNG%2BaFnRjCA@mail.gmail.com>>
>>
>> Content-Type: text/plain; charset="utf-8"
>>
>> Hi,
>>
>> I try to install mosesserver on localhost. I have installed xml-rpc and
>> rebuild moses with no problem.
>>
>> Next i use this command to run the server : *~/mosesdecoder/bin/
>> mosesserver
>> -f working/model/moses.ini --server-port 8999*
>>
>> But it failed with this message :
>>
>> Defined parameters (per moses.ini or switch):
>> config: /home/kamelnebhi/recaser/training/moses.ini
>> distortion-limit: 6
>> feature: UnknownWordPenalty WordPenalty PhrasePenalty
>> PhraseDictionaryMemory name=TranslationModel0 table-limit=20
>> num-features=4
>> path=/home/kamelnebhi/recaser/training/phrase-table.gz input-factor=0
>> output-factor=0 Distortion KENLM lazyken=0 name=LM0 factor=0
>> path=/home/kamelnebhi/recaser/training//cased.srilm.gz order=3
>> input-factors: 0
>> mapping: 0 T 0
>> weight: UnknownWordPenalty0= 1 WordPenalty0= -1 PhrasePenalty0= 0.2
>> TranslationModel0= 0.2 0.2 0.2 0.2 Distortion0= 0.3 LM0= 0.5
>> /home/kamelnebhi/mosesdecoder/bin
>> line=UnknownWordPenalty
>> FeatureFunction: UnknownWordPenalty0 start: 0 end: 0
>> line=WordPenalty
>> FeatureFunction: WordPenalty0 start: 1 end: 1
>> line=PhrasePenalty
>> FeatureFunction: PhrasePenalty0 start: 2 end: 2
>> line=PhraseDictionaryMemory name=TranslationModel0 table-limit=20
>> num-features=4 path=/home/kamelnebhi/recaser/training/phrase-table.gz
>> input-factor=0 output-factor=0
>> FeatureFunction: TranslationModel0 start: 3 end: 6
>> line=Distortion
>> FeatureFunction: Distortion0 start: 7 end: 7
>> line=KENLM lazyken=0 name=LM0 factor=0
>> path=/home/kamelnebhi/recaser/training//cased.srilm.gz order=3
>> FeatureFunction: LM0 start: 8 end: 8
>> Loading the LM will be faster if you build a binary file.
>> Reading /home/kamelnebhi/recaser/training//cased.srilm.gz
>> ----5---10---15---20---25---30---35---40---45---50---55---
>> 60---65---70---75---80---85---90---95--100
>> *The ARPA file is missing <unk>. Substituting log10 probability -100.
>> ************************************************************
>> ***************************************
>> Loading UnknownWordPenalty0
>> Loading WordPenalty0
>> Loading PhrasePenalty0
>> Loading Distortion0
>> Loading LM0
>> Loading TranslationModel0
>> Start loading text SCFG phrase table. Moses format : [3.69361] seconds
>> Reading /home/kamelnebhi/recaser/training/phrase-table.gz
>> ----5---10---15---20---25---30---35---40---45---50---55---
>> 60---65---70---75---80---85---90---95--100
>> ************************************************************
>> ****************************************
>> Erreur de segmentation (core dumped)
>> root@kamelnebhi-MacBookPro:/home/kamelnebhi#
>> /home/kamelnebhi/mosesdecoder/bin/mosesserver -f
>> /home/kamelnebhi/recaser/training/moses.ini --server-port 80
>> Defined parameters (per moses.ini or switch):
>> config: /home/kamelnebhi/recaser/training/moses.ini
>> distortion-limit: 6
>> feature: UnknownWordPenalty WordPenalty PhrasePenalty
>> PhraseDictionaryMemory name=TranslationModel0 table-limit=20
>> num-features=4
>> path=/home/kamelnebhi/recaser/training/phrase-table.gz input-factor=0
>> output-factor=0 Distortion KENLM lazyken=0 name=LM0 factor=0
>> path=/home/kamelnebhi/recaser/training//cased.srilm.gz order=3
>> input-factors: 0
>> mapping: 0 T 0
>> weight: UnknownWordPenalty0= 1 WordPenalty0= -1 PhrasePenalty0= 0.2
>> TranslationModel0= 0.2 0.2 0.2 0.2 Distortion0= 0.3 LM0= 0.5
>> /home/kamelnebhi/mosesdecoder/bin
>> line=UnknownWordPenalty
>> FeatureFunction: UnknownWordPenalty0 start: 0 end: 0
>> line=WordPenalty
>> FeatureFunction: WordPenalty0 start: 1 end: 1
>> line=PhrasePenalty
>> FeatureFunction: PhrasePenalty0 start: 2 end: 2
>> line=PhraseDictionaryMemory name=TranslationModel0 table-limit=20
>> num-features=4 path=/home/kamelnebhi/recaser/training/phrase-table.gz
>> input-factor=0 output-factor=0
>> FeatureFunction: TranslationModel0 start: 3 end: 6
>> line=Distortion
>> FeatureFunction: Distortion0 start: 7 end: 7
>> line=KENLM lazyken=0 name=LM0 factor=0
>> path=/home/kamelnebhi/recaser/training//cased.srilm.gz order=3
>> FeatureFunction: LM0 start: 8 end: 8
>> Loading the LM will be faster if you build a binary file.
>> Reading /home/kamelnebhi/recaser/training//cased.srilm.gz
>> ----5---10---15---20---25---30---35---40---45---50---55---
>> 60---65---70---75---80---85---90---95--100
>> *The ARPA file is missing <unk>. Substituting log10 probability -100.
>> ************************************************************
>> ***************************************
>> Loading UnknownWordPenalty0
>> Loading WordPenalty0
>> Loading PhrasePenalty0
>> Loading Distortion0
>> Loading LM0
>> Loading TranslationModel0
>> Start loading text SCFG phrase table. Moses format : [3.69152] seconds
>> Reading /home/kamelnebhi/recaser/training/phrase-table.gz
>> ----5---10---15---20---25---30---35---40---45---50---55---
>> 60---65---70---75---80---85---90---95--100
>> ************************************************************
>> ****************************************
>> Segmentation fault (core dumped)
>>
>> *Thanks for your help*
>> -------------- next part --------------
>> An HTML attachment was scrubbed...
>> URL: http://mailman.mit.edu/mailman/private/moses-support/
>> attachments/20140407/82302fab/attachment-0001.htm
>>
>> ------------------------------
>>
>> Message: 2
>> Date: Mon, 7 Apr 2014 16:00:47 -0400
>> From: Philipp Koehn <pkoehn@inf.ed.ac.uk <mailto:pkoehn@inf.ed.ac.uk>>
>>
>> Subject: Re: [Moses-support] Monolingual Word alignment
>> To: Mostafa Dehghani <dehghani.mostafa@gmail.com <mailto:
>> dehghani.mostafa@gmail.com>>
>> Cc: "moses-support@mit.edu <mailto:moses-support@mit.edu>" <
>> moses-support@mit.edu <mailto:moses-support@mit.edu>>
>> Message-ID:
>> <CAAFADDBXoZv7=u5RqJaY3brfWOB92yWKRvfeKdz6yrx29m78DA@mail.
>> gmail.com <mailto:u5RqJaY3brfWOB92yWKRvfeKdz6yrx29m78DA@mail.gmail.com>>
>>
>> Content-Type: text/plain; charset=ISO-8859-1
>>
>> Hi,
>>
>> this outcome is not that surprising to me.
>>
>> If you align identical sentences, then translating each word to itself
>> is a pretty good model.
>>
>> Since your goal is paraphrasing words into synonyms, you should
>> rather use methods such as the one proposed by Bannard and
>> Callison-Burch: http://acl.ldc.upenn.edu/P/P05/P05-1074.pdf
>>
>> -phi
>>
>> On Sun, Apr 6, 2014 at 11:11 AM, Mostafa Dehghani
>> <dehghani.mostafa@gmail.com <mailto:dehghani.mostafa@gmail.com>> wrote:
>> > Dear all,
>> >
>> > I am working on a method for Multilingual Information Retrieval. In my
>> > method I expand the text of each document by probabilistically
>> translating
>> > its words to other languages' words (interlingual expansion). However,
>> to
>> > pass some axioms, I need to expand text of each document in its own
>> language
>> > (intralingual expansion). So, beside bilingual word alignments, I need
>> > monolingual word alignments table (that probably contains the alignment
>> of
>> > each word to the words those are related/concurred with that word). To
>> do
>> > so, I used one side of each language sentences and their copy as
>> parallel
>> > corpus. Then I used the following command:
>> >
>> >
>> > train-model.perl -root-dir train -corpus corpus/fr-fr -f fr1 -e fr2
>> > -alignment grow-diag-final-and -reordering msd-bidirectional-fe
>> > -external-bin-dir externalbin -last-step 4
>> >
>> >
>> > such that fr-fr.fr1 fr-fr.fr2 are the same files containing French
>> > sentences.
>> > However, I got f2e and e2f files that are only contain alignments of
>> each
>> > word to itself with probability of 1.
>> > I am wondering is there any parameter that I should set to achieve words
>> > alignments (e2f/f2e) those are proper for intralingual expansion?
>> >
>> > Regards,
>> >
>> > --
>> > Mostafa
>> > ,
>> >
>> > http://khorshid.ut.ac.ir/~m.dehghani <http://khorshid.ut.ac.ir/%
>> 7Em.dehghani>
>> >
>> > _______________________________________________
>> > Moses-support mailing list
>> > Moses-support@mit.edu <mailto:Moses-support@mit.edu>
>>
>> > http://mailman.mit.edu/mailman/listinfo/moses-support
>> >
>>
>>
>> ------------------------------
>>
>> Message: 3
>> Date: Mon, 7 Apr 2014 23:27:07 +0100
>> From: Lucia Specia <lspecia@gmail.com <mailto:lspecia@gmail.com>>
>>
>> Subject: [Moses-support] Call for Participation: Automatic and Manual
>> Metrics for Operational Translation Evaluation
>> To: moses-support@mit.edu <mailto:moses-support@mit.edu>,
>> wmt-tasks@googlegroups.com <mailto:wmt-tasks@googlegroups.com>
>> Message-ID:
>> <CAALeUxzVnsV0xp-uvXOk0Z8qwTkd-JT11FtOporhO0rAS9uiLg@mail.
>> gmail.com <mailto:CAALeUxzVnsV0xp-uvXOk0Z8qwTkd-
>> JT11FtOporhO0rAS9uiLg@mail.gmail.com>>
>>
>> Content-Type: text/plain; charset="iso-8859-1"
>>
>> Dear all,
>>
>> This workshop may be relevant for those of you interested in MT evaluation
>> metrics.
>>
>> ----
>>
>> Automatic and Manual Metrics for Operational Translation Evaluation
>>
>> http://mte2014.github.io/
>>
>> 26 May 2014
>>
>> Workshop at Language Resources and Evaluation Conference (LREC) 2014
>>
>> http://lrec2014.lrec-conf.org
>>
>> In brief:
>>
>> We invite you to join us for an interesting day of work (and play!) as we
>> discuss metrics for machine translation quality assessment and participate
>> in some hands-on task-based translation evaluation.
>>
>> This workshop on Automatic and Manual Metrics for Operational Translation
>> Evaluation (MTE 2014) will be a full-day LREC workshop to be held on
>> Monday, May 26, 2014 in Reykjavik, Iceland. The format of MTE 2014 will be
>> interactive and energizing: a half-day of short presentations and
>> discussion of recent work on machine translation quality assessment,
>> followed by a half-day of hands-on collaborative work with MT metrics that
>> show promise for the prediction of task suitability of MT output. The
>> afternoon hands-on work will follow from the morning's presentations, with
>> some of the hands-on exercises developed directly from the submissions to
>> the workshop.
>>
>> Details:
>>
>> While a significant body of work has been done by the machine translation
>> (MT) research community towards the development and meta-evaluation of
>> automatic metrics to assess overall MT quality, less attention has been
>> dedicated to more operational evaluation metrics aimed at testing whether
>> translations are adequate within a specific context: purpose, end-user,
>> task, etc., and why the MT system fails in some cases. Both of these can
>> benefit from some form of manual analysis. Most work in this area is
>> limited to productivity tests (e.g. contrasting time for human translation
>> and MT post-editing). A few initiatives consider more detailed metrics for
>> the problem, which can also be used to understand and diagnose errors in
>> MT
>> systems. These include the Multidimensional Quality Metrics (MQM) recently
>> proposed by the EU F7 project QTLaunchPad, the TAUS Dynamic Quality
>> Framework, and past projects such as FEMTI, EAGLES and ISLE. Some of these
>> metrics are also applicable to human translation evaluation. A number of
>> task-based metrics have also been proposed for applications such as topic
>> ID / triage and reading comprehension. The purpose of this workshop is to
>> bring together representatives from academia, industry and government
>> institutions to discuss and assess metrics for manual and automatic
>> quality
>> evaluation, with an eye toward how they might be leveraged or further
>> developed into task-based metrics for more objective "fitness for purpose"
>> assessment. We will also consider comparisons to well-established metrics
>> for automatic evaluation such as BLEU, METEOR and others, including
>> reference-less metrics for quality prediction. The workshop will benefit
>> from datasets already collected and manually annotated for translation
>> errors by the QTLaunchPad project (http://www.qt21.eu/launchpad/) and
>> will
>> cover concepts from many the metrics proposed by participants in the
>> half-day of hands-on tasks.
>>
>> Up-to-the-minute information and (most importantly) Registration:
>>
>> Additional details and schedule will be posted at the workshop website
>> http://mte2014.github.io/ as they become available. Register to attend
>> via
>> the LREC registration site at http://lrec2014.lrec-conf.org/
>> en/registration/
>> .
>>
>> We look forward to seeing you there!
>>
>> The MTE 2014 Organizing Committee
>>
>> Keith J. Miller (MITRE)
>>
>> Lucia Specia (University of Sheffield)
>>
>> Kim Harris (GALA and text & form)
>>
>> Stacey Bailey (MITRE)
>> -------------- next part --------------
>> An HTML attachment was scrubbed...
>> URL: http://mailman.mit.edu/mailman/private/moses-support/
>> attachments/20140407/a8dbf5d0/attachment.htm
>>
>> ------------------------------
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
>>
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>>
>> End of Moses-support Digest, Vol 90, Issue 19
>> *********************************************
>>
>>
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>
>
> --
> The University of Edinburgh is a charitable body, registered in
> Scotland, with registration number SC005336.
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140411/cbbcbefc/attachment.htm

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

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


End of Moses-support Digest, Vol 90, Issue 33
*********************************************

0 Response to "Moses-support Digest, Vol 90, Issue 33"

Post a Comment

Subscribe to: Post Comments (Atom)