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: Lattice input and source word range in
EvaluateWhenApplied (Hieu Hoang)
2. Re: Lattice input and source word range in
EvaluateWhenApplied (Marcin Junczys-Dowmunt)
3. Re: Lattice input and source word range in
EvaluateWhenApplied (Hieu Hoang)
4. Bad Accuracy (fatma elzahraa Eltaher)
5. Fwd: Problem Reading binarised model :: ttable does not exit
(Harshit Gupta)
----------------------------------------------------------------------
Message: 1
Date: Tue, 30 Jun 2015 20:28:43 +0400
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] Lattice input and source word range in
EvaluateWhenApplied
To: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbjaiTnWUx-==mVJ1KAvxnL2FBFc_y1RQxyd1veEa8obzw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
cur_hypo.GetTranslationOption().GetInputPath()
i hope
Hieu Hoang
Researcher
New York University, Abu Dhabi
http://www.hoang.co.uk/hieu
On 30 June 2015 at 19:30, Marcin Junczys-Dowmunt <junczys@amu.edu.pl> wrote:
> Hi,
> is there a way to find the current source phrase (input path) for
> lattices in the following feature function hook?
>
> FFState* EvaluateWhenApplied(
> const Hypothesis& cur_hypo,
> const FFState* prev_state,
> ScoreComponentCollection* accumulator)
>
> Specifically I want to use the OSM with lattice input, but it is only
> written for sentence input. If I am not very wrong it should not easy to
> modify if only I can get the plain source word range from a lattice.
> Thanks,
> Marcin
> _______________________________________________
> 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/20150630/a6b7d05a/attachment-0001.htm
------------------------------
Message: 2
Date: Tue, 30 Jun 2015 18:41:39 +0200
From: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Subject: Re: [Moses-support] Lattice input and source word range in
EvaluateWhenApplied
To: Hieu Hoang <hieuhoang@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID: <5592C6C3.6080301@amu.edu.pl>
Content-Type: text/plain; charset=UTF-8; format=flowed
Thanks, looks good. Does cur_hypo.GetCurrSourceWordsRange() still make
sense in the context of lattices?
On 30.06.2015 18:28, Hieu Hoang wrote:
> cur_hypo.GetTranslationOption().GetInputPath()
>
> i hope
>
> Hieu Hoang
> Researcher
> New York University, Abu Dhabi
> http://www.hoang.co.uk/hieu
>
> On 30 June 2015 at 19:30, Marcin Junczys-Dowmunt <junczys@amu.edu.pl
> <mailto:junczys@amu.edu.pl>> wrote:
>
> Hi,
> is there a way to find the current source phrase (input path) for
> lattices in the following feature function hook?
>
> FFState* EvaluateWhenApplied(
> const Hypothesis& cur_hypo,
> const FFState* prev_state,
> ScoreComponentCollection* accumulator)
>
> Specifically I want to use the OSM with lattice input, but it is only
> written for sentence input. If I am not very wrong it should not
> easy to
> modify if only I can get the plain source word range from a lattice.
> Thanks,
> Marcin
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
------------------------------
Message: 3
Date: Tue, 30 Jun 2015 21:44:48 +0400
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] Lattice input and source word range in
EvaluateWhenApplied
To: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Cc: moses-support <moses-support@mit.edu>
Message-ID: <5592D590.207@gmail.com>
Content-Type: text/plain; charset=utf-8; format=flowed
the start and end points are still start and end. But the width no
longer means the number of words. I think Chris Dyer added the
floyd-walshall algorithm to find the shortest path between 2 points, but
that doesn't mean the number of words either.
The size of the phrase in the InputPath is the number of words
On 30/06/2015 20:41, Marcin Junczys-Dowmunt wrote:
> Thanks, looks good. Does cur_hypo.GetCurrSourceWordsRange() still make
> sense in the context of lattices?
>
> On 30.06.2015 18:28, Hieu Hoang wrote:
>> cur_hypo.GetTranslationOption().GetInputPath()
>>
>> i hope
>>
>> Hieu Hoang
>> Researcher
>> New York University, Abu Dhabi
>> http://www.hoang.co.uk/hieu
>>
>> On 30 June 2015 at 19:30, Marcin Junczys-Dowmunt <junczys@amu.edu.pl
>> <mailto:junczys@amu.edu.pl>> wrote:
>>
>> Hi,
>> is there a way to find the current source phrase (input path) for
>> lattices in the following feature function hook?
>>
>> FFState* EvaluateWhenApplied(
>> const Hypothesis& cur_hypo,
>> const FFState* prev_state,
>> ScoreComponentCollection* accumulator)
>>
>> Specifically I want to use the OSM with lattice input, but it is
>> only
>> written for sentence input. If I am not very wrong it should not
>> easy to
>> modify if only I can get the plain source word range from a lattice.
>> Thanks,
>> Marcin
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>>
>
>
--
Hieu Hoang
Researcher
New York University, Abu Dhabi
http://www.hoang.co.uk/hieu
------------------------------
Message: 4
Date: Wed, 1 Jul 2015 02:22:30 +0200
From: fatma elzahraa Eltaher <fatmaeltaher@gmail.com>
Subject: [Moses-support] Bad Accuracy
To: moses-support@mit.edu
Message-ID:
<CAOW1BbQm0zQ9OGu5b5f3Eqtp1dzZQhKX0UnxKB9u_fE6HeB+Wg@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Dear All,
I trained my model with 4633 words ,test it with 342 word and only 99 word
was right . How can I increase the accuracy of my model?
note: I use 1000 word for tuning.
thank you,
Fatma El-Zahraa El -Taher
Teaching Assistant at Computer & System department
Faculty of Engineering, Azhar University
Email : fatmaeltaher@gmail.com
mobile: +201141600434
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150701/94659b3d/attachment-0001.htm
------------------------------
Message: 5
Date: Wed, 1 Jul 2015 14:24:23 +0530
From: Harshit Gupta <harshitgupta165@gmail.com>
Subject: [Moses-support] Fwd: Problem Reading binarised model ::
ttable does not exit
To: moses-support@mit.edu
Message-ID:
<CAHgj_vuCapTRd7WYRHGHbA2VOXEoCq7b3SpDASy8HjDvFpMA8Q@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Hi
i am facing problem while reading *Reading binarised model* please help me
out of this problem.
i will explain my step :
for Phrase model
Step 1 : ~/working$ ~/mosesdecoder-RELEASE-3.0/bin/processPhraseTableMin
-in train/model/phrase-table.gz -nscores 4 -out binarised-model/phrase-table
For Reordering model
Step 2: ~/mosesdecoder-RELEASE-3.0/bin/processLexicalTable -in
train/model/reordering-table.wbe-msd-bidirectional-fe.gz -out
binarised-model/reordering-table
Step 3 : Change in moses.ini file
Change PhraseDictionaryMemory to PhraseDictionaryBinary
Set the path of the PhraseDictionary feature to point to
/home/working/binarised-model/phrase-table
Set the path of the LexicalReordering feature to point to
/home/working/binarised-model/reordering-table
Step 4 Testing Translation
working$ echo "The house was built in 14th century" |
~/mosesdecoder-RELEASE-3.0/bin/moses -f
/home/working/binarised-model/moses.ini
Defined parameters (per moses.ini or switch):
config: /home/working/binarised-model/moses.ini
distortion-limit: 6
feature: UnknownWordPenalty WordPenalty PhrasePenalty
PhraseDictionaryBinary name=TranslationModel0 num-features=4
path=/home/working/binarised-model/phrase-table.minphr input-factor=0
output-factor=0 LexicalReordering name=LexicalReordering0 num-features=6
type=wbe-msd-bidirectional-fe-allff input-factor=0 output-factor=0
path=/home/working/binarised-model/reordering-table.* Distortion KENLM
lazyken=0 name=LM0 factor=0 path=/home/lm/test.en-hi.blm.hi order=3
input-factors: 0
mapping: 0 T 0
weight: LexicalReordering0= 0.0639361 0.0474959 0.0356438 0.0306086
0.0167372 0.0750312 Distortion0= 0.0116104 LM0= 0.0314945 WordPenalty0=
-0.109872 PhrasePenalty0= -0.22791 TranslationModel0= 0.0253477 0.00221282
0.311753 -0.0103464 UnknownWordPenalty0= 1
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=PhraseDictionaryBinary name=TranslationModel0 num-features=4
path=/home/working/binarised-model/phrase-table.minphr input-factor=0
output-factor=0
FeatureFunction: TranslationModel0 start: 3 end: 6
line=LexicalReordering name=LexicalReordering0 num-features=6
type=wbe-msd-bidirectional-fe-allff input-factor=0 output-factor=0
path=/home/working/binarised-model/reordering-table.*
FeatureFunction: LexicalReordering0 start: 7 end: 12
Initializing LexicalReordering..
line=Distortion
FeatureFunction: Distortion0 start: 13 end: 13
line=KENLM lazyken=0 name=LM0 factor=0 path=/home/lm/test.en-hi.blm.hi
order=3
FeatureFunction: LM0 start: 14 end: 14
Loading UnknownWordPenalty0
Loading WordPenalty0
Loading PhrasePenalty0
Loading LexicalReordering0
binary file loaded, default OFF_T: -1
Loading Distortion0
Loading LM0
Loading TranslationModel0
Created input-output object : [0.011] seconds
Translating: The house was built in 14th century
terminate called after throwing an instance of 'util::Exception'
what(): moses/PDTAimp.cpp:173 in void Moses::PDTAimp::Create(const
std::vector<long unsigned int>&, const std::vector<long unsigned int>&,
const string&, const std::vector<float>&) threw util::Exception'.
bin ttable does not exist
Aborted (core dumped)
Please suggest some idea to solve this problem
Regards
--
Harshit Gupta
Third Year Undergraduate
Electrical Engineering
IIT Madras
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150701/1b3f7152/attachment.htm
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 105, Issue 1
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 105, Issue 1"
Post a Comment