Moses-support Digest, Vol 89, Issue 34

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. Exception: bitset::set (Rajen Chatterjee)
2. Giza++ HMMTable readJumps implementation (Nima Pourdamghani)
3. TSD 2014 - Last Call for Papers (TSD 2014)
4. Re: Use of uninitialized value $___REORDERING_FACTORS (Hieu Hoang)


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

Message: 1
Date: Sun, 16 Mar 2014 16:33:24 +0000
From: Rajen Chatterjee <rajen.k.chatterjee@gmail.com>
Subject: [Moses-support] Exception: bitset::set
To: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CAC4-+NzK4Q722u7rgTGjp6pqQL7HWA1y6JQJGiXNLh7ggo3KaA@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

Hi All,

While running decoder I am getting following exception:

Start loading PhraseTable
/home/rajen/Public/SMT/experiments/Project/result/gorn/en-hi/moses_data/model/phrase-table.0,4-0.gz
: [32.062] seconds
filePath:
/home/rajen/Public/SMT/experiments/Project/result/gorn/en-hi/moses_data/model/phrase-table.0,4-0.gz
ScoreProducer: PhraseModel start: 10 end: 15
Exception: bitset::set

Any idea how to solve this?


--
-Regards,
Rajen Chatterjee.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140316/75acc393/attachment-0001.htm

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

Message: 2
Date: Sun, 16 Mar 2014 09:49:46 -0700
From: Nima Pourdamghani <damghani@isi.edu>
Subject: [Moses-support] Giza++ HMMTable readJumps implementation
To: moses-support@mit.edu
Message-ID:
<CA+ZdAL7V5xeG28=4+VUSi1gfgy3Of_XLERQXVz6_JQ6uggVsrg@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

I need to load my probability tables into Giza++. Currently I am working
with HMM model. I've managed to load the t-table, but loading the a-table
(i.e. h-table) is not implemented in the version that I have (the body of
readJumps function in HMMTables.cpp file is empty).
Is there an implementation of this function available? If not how can one
implement it?

Cheers
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140316/7ad11953/attachment-0001.htm

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

Message: 3
Date: Mon, 17 Mar 2014 09:58:45 +0100
From: TSD 2014 <xrambous@aurora.fi.muni.cz>
Subject: [Moses-support] TSD 2014 - Last Call for Papers
To: tsd2014@tsdconference.org
Message-ID: <E1WPTNd-0002dv-7R@aurora.fi.muni.cz>

*********************************************************
TSD 2014 - LAST CALL FOR PAPERS
*********************************************************

Seventeenth International Conference on TEXT, SPEECH and DIALOGUE (TSD 2014)
Brno, Czech Republic, 8-12 September 2014
http://www.tsdconference.org/

THE SUBMISSION DEADLINE:

March 22 2014 ............ Submission of full papers

The submission will be closed during the next working day after the
deadline - for individual extension requirements please contact the
organizers (tsd2014@tsdconference.org).

KEYNOTE SPEAKERS

Ralph Grishman, New York University, USA
Bernardo Magnini, FBK - Fondazione Bruno Kessler, Italy
Salim Roukos, IBM, USA


The conference is organized by the Faculty of Informatics, Masaryk
University, Brno, and the Faculty of Applied Sciences, University of
West Bohemia, Pilsen. The conference is supported by International
Speech Communication Association.

Venue: Brno, Czech Republic


TSD SERIES

TSD series evolved as a prime forum for interaction between researchers in
both spoken and written language processing from all over the world.
Proceedings of TSD form a book published by Springer-Verlag in their
Lecture Notes in Artificial Intelligence (LNAI) series. TSD Proceedings
are regularly indexed by Thomson Reuters Conference Proceedings Citation
Index. Moreover, LNAI series are listed in all major citation databases
such as DBLP, SCOPUS, EI, INSPEC or COMPENDEX.


TOPICS

Topics of the conference will include (but are not limited to):

Corpora and Language Resources (monolingual, multilingual,
text and spoken corpora, large web corpora, disambiguation,
specialized lexicons, dictionaries)

Speech Recognition (multilingual, continuous, emotional
speech, handicapped speaker, out-of-vocabulary words,
alternative way of feature extraction, new models for
acoustic and language modelling)

Tagging, Classification and Parsing of Text and Speech
(morphological and syntactic analysis, synthesis and
disambiguation, multilingual processing, sentiment analysis,
credibility analysis, automatic text labeling, summarization,
authorship attribution)

Speech and Spoken Language Generation (multilingual, high
fidelity speech synthesis, computer singing)

Semantic Processing of Text and Speech (information
extraction, information retrieval, data mining, semantic web,
knowledge representation, inference, ontologies, sense
disambiguation, plagiarism detection)

Integrating Applications of Text and Speech Processing
(machine translation, natural language understanding,
question-answering strategies, assistive technologies)

Automatic Dialogue Systems (self-learning, multilingual,
question-answering systems, dialogue strategies, prosody in
dialogues)

Multimodal Techniques and Modelling (video processing, facial
animation, visual speech synthesis, user modelling, emotions
and personality modelling)

Papers on processing of languages other than English are strongly
encouraged.


PROGRAM COMMITTEE

Hynek Hermansky, USA (general chair)
Eneko Agirre, Spain
Genevieve Baudoin, France
Paul Cook, Australia
Jan Cernocky, Czech Republic
Simon Dobrisek, Slovenia
Karina Evgrafova, Russia
Darja Fiser, Slovenia
Radovan Garabik, Slovakia
Alexander Gelbukh, Mexico
Louise Guthrie, GB
Jan Hajic, Czech Republic
Eva Hajicova, Czech Republic
Yannis Haralambous, France
Ludwig Hitzenberger, Germany
Jaroslava Hlavacova, Czech Republic
Ales Horak, Czech Republic
Eduard Hovy, USA
Maria Khokhlova, Russia
Daniil Kocharov, Russia
Ivan Kopecek, Czech Republic
Valia Kordoni, Germany
Steven Krauwer, The Netherlands
Siegfried Kunzmann, Germany
Natalija Loukachevitch, Russia
Vaclav Matousek, Czech Republic
Diana McCarthy, United Kingdom
France Mihelic, Slovenia
Hermann Ney, Germany
Elmar Noeth, Germany
Karel Oliva, Czech Republic
Karel Pala, Czech Republic
Nikola Pavesic, Slovenia
Fabio Pianesi, Italy
Maciej Piasecki, Poland
Adam Przepiorkowski, Poland
Josef Psutka, Czech Republic
James Pustejovsky, USA
German Rigau, Spain
Leon Rothkrantz, The Netherlands
Anna Rumshisky, USA
Milan Rusko, Slovakia
Mykola Sazhok, Ukraine
Pavel Skrelin, Russia
Pavel Smrz, Czech Republic
Petr Sojka, Czech Republic
Stefan Steidl, Germany
Georg Stemmer, Germany
Marko Tadic, Croatia
Tamas Varadi, Hungary
Zygmunt Vetulani, Poland
Pascal Wiggers, The Netherlands
Yorick Wilks, GB
Marcin Wolinski, Poland
Victor Zakharov, Russia


FORMAT OF THE CONFERENCE

The conference program will include presentation of invited papers,
oral presentations, and poster/demonstration sessions. Papers will
be presented in plenary or topic oriented sessions.

Social events including a trip in the vicinity of Brno will allow
for additional informal interactions.


SUBMISSION OF PAPERS

Authors are invited to submit a full paper not exceeding 8 pages
formatted in the LNCS style (see below). Those accepted will be
presented either orally or as posters. The decision about the
presentation format will be based on the recommendation of the
reviewers. The authors are asked to submit their papers using the
on-line form accessible from the conference website.

Papers submitted to TSD 2014 must not be under review by any other
conference or publication during the TSD review cycle, and must not be
previously published or accepted for publication elsewhere.

As reviewing will be blind, the paper should not include the authors'
names and affiliations. Furthermore, self-references that reveal the
author's identity, e.g., "We previously showed (Smith, 1991) ...",
should be avoided. Instead, use citations such as "Smith previously
showed (Smith, 1991) ...". Papers that do not conform to the
requirements above are subject to be rejected without review.

The authors are strongly encouraged to write their papers in TeX or
LaTeX formats. These formats are necessary for the final versions of
the papers that will be published in the Springer Lecture Notes.
Authors using a WORD compatible software for the final version must
use the LNCS template for WORD and within the submit process ask the
Proceedings Editors to convert the paper to LaTeX format. For this
service a service-and-license fee of CZK 2000 will be levied
automatically.

The paper format for review has to be either PDF or PostScript file
with all required fonts included. Upon notification of acceptance,
presenters will receive further information on submitting their
camera-ready and electronic sources (for detailed instructions on the
final paper format see
http://www.springer.de/comp/lncs/authors.html#Proceedings, Sample File
typeinst.zip).

Authors are also invited to present actual projects, developed
software or interesting material relevant to the topics of the
conference. The presenters of demonstrations should provide an
abstract not exceeding one page. The demonstration abstracts will not
appear in the conference proceedings.


IMPORTANT DATES

March 22 2014 ............ Submission of full papers
May 15 2014 .............. Notification of acceptance
May 31 2014 .............. Final papers (camera ready) and registration
August 3 2014 ............ Submission of demonstration abstracts
August 10 2014 ........... Notification of acceptance for
demonstrations sent to the authors
September 8-12 2014 ...... Conference date

Submission of abstracts serves for better organization of the review
process only - for the actual review a full paper submission is
necessary.

The accepted conference contributions will be published in proceedings
that will be made available to participants at the time of the
conference.


OFFICIAL LANGUAGE

The official language of the conference is English.


ACCOMMODATION

The organizing committee will arrange discounts on accommodation in
the 4-star hotel at the conference venue. The current prices of the
accommodation will be available at the conference website.


ADDRESS

All correspondence regarding the conference should be
addressed to

Ales Horak, TSD 2014
Faculty of Informatics, Masaryk University
Botanicka 68a, 602 00 Brno, Czech Republic
phone: +420-5-49 49 18 63
fax: +420-5-49 49 18 20
email: tsd2014@tsdconference.org

The official TSD 2014 homepage is: http://www.tsdconference.org/


LOCATION

Brno is the second largest city in the Czech Republic with a
population of almost 400.000 and is the country's judiciary and
trade-fair center. Brno is the capital of South Moravia, which is
located in the south-east part of the Czech Republic and is known
for a wide range of cultural, natural, and technical sights.
South Moravia is a traditional wine region. Brno had been a Royal
City since 1347 and with its six universities it forms a cultural
center of the region.

Brno can be reached easily by direct flights from London, Moscow,
and Eindhoven, and by trains or buses from Prague (200 km) or Vienna
(130 km).

For the participants with some extra time, nearby places may
also be of interest. Local ones include: Brno Castle now called
Spilberk, Veveri Castle, the Old and New City Halls, the
Augustine Monastery with St. Thomas Church and crypt of Moravian
Margraves, Church of St. James, Cathedral of St. Peter & Paul,
Cartesian Monastery in Kralovo Pole, the famous Villa Tugendhat
designed by Mies van der Rohe along with other important
buildings of between-war Czech architecture.

For those willing to venture out of Brno, Moravian Karst with
Macocha Chasm and Punkva caves, battlefield of the Battle of
three emperors (Napoleon, Russian Alexander and Austrian Franz
- Battle by Austerlitz), Chateau of Slavkov (Austerlitz),
Pernstejn Castle, Buchlov Castle, Lednice Chateau, Buchlovice
Chateau, Letovice Chateau, Mikulov with one of the largest Jewish
cemeteries in Central Europe, Telc - a town on the UNESCO
heritage list, and many others are all within easy reach.


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

Message: 4
Date: Mon, 17 Mar 2014 09:25:28 +0000
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] Use of uninitialized value
$___REORDERING_FACTORS
To: Peter Kleiweg <p.c.j.kleiweg@rug.nl>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbh-0jWQsvo7v95bCdcvaXZW1P71HYNc7kQ4WXJHdd5X+Q@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

On 15 March 2014 19:58, Peter Kleiweg <p.c.j.kleiweg@rug.nl> wrote:

>
> Hi all,
>
> I am trying to do factored translation.
>
> I have an input language (en) with these factors:
>
> 0. word
> 1. lemma
> 2. pos
> 3. rel
>
> I have a target language (nl) with these factors:
>
> 0. word
> 1. lemma
> 2. pos
> 3. postag
> 4. rel
>
> TRAINING
>
> I want to use word(0), lemma(1) and pos(2) from source language (en),
> and word(0), lemma(1), postag(3) from target language (nl).
>
> I run this command:
>
> nohup /net/aps/64/opt/moses/mosesdecoder/scripts/training/train-model.perl
> \
> -cores 12 \
> -root-dir train \
> -corpus
> /net/aistaff/kleiweg/moses/europarl/factored/corpus/train-small.clean \
> -f en -e nl -alignment grow-diag-final-and -reordering
> msd-bidirectional-fe \
> --lm 0:3:/net/aistaff/kleiweg/moses/europarl/factored/lm/blm.nl-word:8 \
> --lm 3:3:/net/aistaff/kleiweg/moses/europarl/factored/lm/blm.nl-postag:8
> \
> --translation-factors 1-1+2-3+0-0,3 \
> --generation-factors 1-3+1,3-0 \
> --decoding-steps t0,g0,t1,g1:t2 \
> -external-bin-dir /net/aps/64/opt/moses/mgizapp/bin \
> -mgiza \
> -mgiza-cpus=12 \
> > training.out \
> 2> training.err &
>
> Did I specify the right translation-factors, generation-factors
> and decoding-steps?
>
That looks ok, there's nothing that contradict each other.

whether it's 'right' depends on your point of view. Personally, I try to
make the factored models as easy as possible. The complicated models with
multiple translation models & generation models make too much independence
assumptions.


> Did I specify the right language models?
>
it should run

>
> Should I specify --alignment-factors, like this:
>
> --alignment-factors 1,2-1,3
>
up to you

>
> Training ends with these lines on stderr:
>
> (9) create moses.ini @ Sat Mar 15 17:19:20 CET 2014
> Use of uninitialized value $___REORDERING_FACTORS in split at
> /net/aps/64/opt/moses/mosesdecoder/scripts/training/train-model.perl line
> 1997.
>
> Should I specify --reordering-factors ? What does this do? What
> do I specify? All I can find in the manual is this:
>
> "Reordering tables can be trained with --reordering-factors.
> Syntax is the same as for translation factors."
>
> That isn't very helpful.
>
> it specifies the factors to use when training the lexicalised reordering
model
http://www.statmt.org/moses/?n=FactoredTraining.BuildReorderingModel

The model that was created seems to be working (even though step
> 9 of training gave an error), but it's slow, 10 minutes or more
> for a sentence, where unfactored translation only took a few seconds.
>
because you have a complicated factored model. It does a cross-product of
all the translation model & generation models

>
> TUNING
>
> What type of data should I give mert-moses.pl to work with? I
> noticed the source language should only have factors 0, 1 and 2,
> or I get an error. What factors should there be in the target
> language?
>
>
>
> --
> Peter Kleiweg
> http://pkleiweg.home.xs4all.nl/
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>



--
Hieu Hoang
Research Associate
University of Edinburgh
http://www.hoang.co.uk/hieu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140317/896dd063/attachment.htm

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

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


End of Moses-support Digest, Vol 89, Issue 34
*********************************************

Tweet