Moses-support Digest, Vol 163, Issue 5

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. Call for Papers: EMNLP 2020 Fifth Conference on Machine
Translation (WMT20) (Barry Haddow)
2. Re: Word Lattice Input (Hieu Hoang)
3. Second CfP and Important Updates: WMT 2020 Shared Task on
Parallel Corpus Filtering and Alignment (Philipp Koehn)


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

Message: 1
Date: Thu, 14 May 2020 21:37:55 +0100
From: Barry Haddow <bhaddow@inf.ed.ac.uk>
Subject: [Moses-support] Call for Papers: EMNLP 2020 Fifth Conference
on Machine Translation (WMT20)
To: moses-support <moses-support@mit.edu>
Message-ID: <9b92e1eb-70d6-9729-5925-ab12a3ca0767@inf.ed.ac.uk>
Content-Type: text/plain; charset="utf-8"

EMNLP 2020 FiFTH CONFERENCE ON MACHINE TRANSLATION (WMT20)

November 19-20th, Online

http://www.statmt.org/wmt20


*** CALL FOR PAPERS ***

We invite the submission of scientific papers on topics related to MT.
Topics of interest include, but are not limited to:

* MT models (neural, statistical etc. )
* analysis of neural models for MT
* using comparable corpora for MT
* selection and preparation of data for MT
* semi-supervised and unsupervised learning for MT, transfer learning
* multilingual MT
* incorporating linguistic information into MT
* MT inference
* manual and automatic methods for evaluating MT
* quality estimation for MT


SHARED TASKS

There are several MT-related shared tasks associated with the workshop.
These include several translation tasks, automatic post-editing,
lifelong learning, automatic evaluation, targeted evaluation (test
suites) and quality estimation. See the conference website for more
details, and subscribe to the mailing list
(https://groups.google.com/forum/#!forum/wmt-tasks)

PAPER SUBMISSION INFORMATION

Submissions will consist of full research papers? of 6-10 pages, plus
additional pages for references, formatted following the EMNLP 2020
guidelines. In addition, shared task participants will be invited to
submit short papers (suggested length 4-6 pages) describing their
systems or their evaluation metrics. Both submission and review processes
will be handled electronically.

We encourage individuals who are submitting research papers to
evaluate their approaches using the training resources provided by
this workshop and past workshops, so that their experiments can be
repeated by others using these publicly available corpora.

IMPORTANT DATES

Paper submissions:

Paper submission deadline: August 15th, 2020
Notification of acceptance: September 29th, 2020
Camera-ready deadline: October 10th, 2020
Online conference: November 19-20th, 2020



Barry Haddow
(On behalf of the organisers)

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20200514/160e6a1d/attachment-0001.html
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: not available
Url: http://mailman.mit.edu/mailman/private/moses-support/attachments/20200514/160e6a1d/attachment-0001.pl

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

Message: 2
Date: Thu, 14 May 2020 16:03:57 -0700
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] Word Lattice Input
To: Moses Visperas <moses.visperas@eee.upd.edu.ph>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbhYvgAVO7j3+_OO5xnmCAJn8Hdm-MWLowdrb153nq4bxg@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

you might wanna take a look at some of the lattice regression tests, eg

https://github.com/moses-smt/moses-regression-tests/blob/master/tests/phrase.lattice-surface/moses.ini
specifically, add the lines that says InputFeature

The error is because --weight-i 1 is the old way of specifying the input
feature.

Hieu Hoang
http://statmt.org/hieu


On Wed, 13 May 2020 at 23:00, Moses Visperas <moses.visperas@eee.upd.edu.ph>
wrote:

> So I followed the tutorial for the baseline system and I want to try using
> a Lattice input. I made a test.plf file which contains 2 sentences
> formatted as shown in the manual (6.5.1) and was checked by the checkplf
> program.
>
> I used this command :
> ~/mosesdecoder/bin/moses -f moses.ini --inputtype 2 --max-phrase-length 13
> --weight-i 1 < test.plf > PLF13.en 2> PLF.out
> and I got an erro saying:
> Exception: moses/Parameter.cpp:572 in bool
> Moses::Parameter::LoadParam(int, const char**) threw util::Exception.
> Don't mix old and new ini file format
> and when I removed the " --weight-i 1" argument I get this :
> Exception: moses/ConfusionNet.cpp:72 in
> Moses::ConfusionNet::ConfusionNet(const ptr&) threw util::Exception because
> `InputFeature::InstancePtr() == __null'.
> Input feature must be specified
> Anyone can help me on how to set the input feature?
> _______________________________________________
> 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/20200514/32199ac8/attachment-0001.html

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

Message: 3
Date: Fri, 15 May 2020 11:02:48 -0400
From: Philipp Koehn <phi@jhu.edu>
Subject: [Moses-support] Second CfP and Important Updates: WMT 2020
Shared Task on Parallel Corpus Filtering and Alignment
To: <wmt-tasks@googlegroups.com>, Moses Support
<moses-support@mit.edu>, "corpora@uib.no" <CORPORA@uib.no>
Message-ID:
<CAAFADDDkuDqk5Wkhw0qtvmNYU4Fn6GddxFqCCHGtAOUOX0ZFAA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Second Call for ParticipationWMT 2020 Shared TaskParallel Corpus Filtering
and Alignment for Low-Resource Conditions
SEE UPDATES BELOW

http://www.statmt.org/wmt20/parallel-corpus-filtering.html

We announce and call for participation in the WMT 2020 shared task on
assessing the quality of sentence pairs in a parallel corpus.

- In the WMT18 shared task on parallel corpus filtering
<http://www.statmt.org/wmt18/parallel-corpus-filtering.html>, we posed
the challenge of a noisy web-crawled parallel corpus for German-English and
asked participants to score each sentence pair. These quality scores were
used to select subsets of the corpus, consisting of the highest-scoring
sentence pairs, train statistical and neural machine translation systems on
them, and evaluate these on a set of test sets.
- In the WMT19 shared task on parallel corpus filtering for low resource
conditions <http://www.statmt.org/wmt19/parallel-corpus-filtering.html>,
we followed the same protocol, but this time for Nepali-English and
Sinhala-English. For low-resource language pairs like these, both existing
clean parallel corpora and the to-be-scored noisy web-crawled data comes in
smaller amounts and lower quality.

This year, we pose two different language pairs, Khmer-English and
Pashto-English. In addition to the task of computing quality scores for the
purpose of filtering, we also allow for the re-alignment of sentence pairs
from document pairs.
IMPORTANT UPDATESIn sync with changes in deadlines for EMNLP and WMT, we
also pushed back all deadlines by 1 month to:
Submission deadline for subsampled sets August 1, 2020
System descriptions due August 15, 2020
Announcement of results August 29, 2020
Paper notification September 29, 2020
Camera-ready for system descriptions October 10, 2020MISSING SENTENCE PAIRS
IN DOCUMENT PAIRSUnfortunately, some of the document pairs are missing for
sentence pairs included in the sentence aligned set. So, if you are running
your own document alignment, we provided sets of sentence pairs to be
included to the sentence pairs that you extract yourself from the document
pairs (see Section "RAW CORPUS DOWNLOAD / Document Pairs" on the web page).
BASELINE RESULTS
We noticed that with different GPU hardware, different scores (?1 BLEU
point) are obtained on the same sets. There is also some variance with
different seeds. While you may observe different numbers from the ones
listed on the web page, all final scoring will be done on identical
hardware for all participants to ensure fair assessments.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20200515/5f1a3970/attachment.html

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

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


End of Moses-support Digest, Vol 163, Issue 5
*********************************************

Tweet