Re: [Moses-support] Word Lattice Input

[Hieu Hoang]

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

[Moses-support] Call for Papers: EMNLP 2020 Fifth Conference on Machine Translation (WMT20)

[Barry Haddow]

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)

The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support