Moses-support Digest, Vol 168, Issue 12

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. Error when N-Gram exceeds 6 (fadi ghawanmeh)
2. Researcher, part-time 75% at DFKI Saarbr?cken. PhD position
in multi-modal sign language translation with deep learning.
(Cristina Espa?a-Bonet)


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

Message: 1
Date: Mon, 26 Oct 2020 10:35:04 +0000 (UTC)
From: fadi ghawanmeh <fadighawanmeh@yahoo.com>
Subject: [Moses-support] Error when N-Gram exceeds 6
To: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID: <1069657928.2518218.1603708504577@mail.yahoo.com>
Content-Type: text/plain; charset="utf-8"

Dears,
I am a PhD student and I am experimenting with Moses SMT. I noticed that when the N-Gram exceeds six, I get an error. I hope this message helps explaining the issue:
RROR: Failed to run'/home/fadiko/mosesdecoder/bin/moses -threads 8 -configfiltered/moses.ini -show-weights'. at/home/fadiko/mosesdecoder/scripts/training/mert-moses.pl line 1775.

testing ...

computing BLEU ...

Use of uninitialized value$length_reference in numeric eq (==) at/home/fadiko/mosesdecoder/scripts/generic/multi-bleu.perl line 148.
Do you have any idea on howto handle this issue?
Best,
Fadi AL-GHAWANMEHPhD student at the University of Lorraine
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20201026/b920757d/attachment.html

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

Message: 2
Date: Thu, 29 Oct 2020 15:17:53 +0100
From: Cristina Espa?a-Bonet <cristinae@dfki.de>
Subject: [Moses-support] Researcher, part-time 75% at DFKI
Saarbr?cken. PhD position in multi-modal sign language translation
with deep learning.
To: moses-support <moses-support@mit.edu>
Message-ID:
<CAKehm8Bo3uChteGuthTaeQJ1jZLoPUg2rbZr+xdqHiOji=mgqw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

[Apologies for cross-postings]

----------------------------------------------------------------------------------------------------------------------------------------------------------------------
Researcher, part-time 75% at DFKI Saarbr?cken. PhD position in
multi-modal sign language translation with deep learning
----------------------------------------------------------------------------------------------------------------------------------------------------------------------

The MT group at DFKI Saarbr?cken is looking for a PhD researcher in sign
language translation using deep learning.

*Key responsibilities: *
- Research and development of novel technologies for sign language (SL)
translation and interpretation
- Design of end-to-end architectures text-to-SL and SL-to-text
- Modality combinations(text, image, video and sensors)
- Design of deep learning modules for modality conversion
- Contribution to scientific publications
- Possibility of teaching at Saarland University

*Desired qualifications: *
- Master in CS (alternatively CL, NLP or related)
- Strong background in machine learning and deep learning
- Excellent problem solving skills
- Excellent programming skills, especially in Python (PyTorch and/or
Tensorflow libraries). Java, bash and C are an asset
- Excellent communication skills and command of written and oral English
(German not required but an asset)

*Application:*
Applications should include a short cover letter, a CV, a brief summary of
research interests, and contact information for three references. Please
submit your application by November 30, 2020 as PDF to Dr. Cristina Espa?a
i Bonet (cristinae@dfki.de) indicating your earliest possible start date.
The position remains open until filled.

*Working environment:*
The post is part of the ?Multilinguality and Language Technology? (MLT) lab
at DFKI (the German Research Center for Artificial Intelligence) in
Saarbr?cken, Germany. The lab is headed by Prof. Josef van Genabith. MLT
consists of highly international teams combining basic research and
applications. MLT has research groups in MT, QA/IE, human-robot
communication, and data and resources. DFKI is one of the leading AI
centers worldwide, with several sites in Germany. DFKI Saarbr?cken is part
of the Saarland University (UdS) Informatics Campus. UdS has exceptionally
strong CS and CL schools, a Max Planck Institute for Informatics, a Max
Planck Institute for Software Systems, the Center for Bioinformatics, and
the CISPA Helmholz Center for Information Security.

*Geographic environment: *
Saarbr?cken (http://www.saarbruecken.de/en) is the capital of Saarland,
one of the smaller Federal States in Germany, located right in the heart
of Europe and a cultural center of the border region of Germany, France and
Luxembourg. Frankfurt and Paris are less than 2 hours by train. Living
costs are moderate in comparison with other large cities in Germany and
Europe.

*Selected MLT MT group publications in 2020:*
- Chowdhury et al. Understanding Translationese in Multi-View Embedding
Spaces. COLING 2020.
- Pal et al. The Transference Architecture for Automatic Post-Editing.
COLING 2020.
- Ruiter et al. Self-Induced Curriculum Learning in Self-Supervised Neural
Machine Translation. EMNLP 2020.
- Zhang et al. Translation Quality Estimation by Jointly Learning to Score
and Rank. EMNLP 2020.
- Xu et al. Dynamically Adjusting Transformer Batch Size by Monitoring
Gradient Direction Change. ACL 2020.
- Xu et al. Learning Source Phrase Representations for Neural Machine
Translation. ACL 2020.
- Xu et al. Lipschitz Constrained Parameter Initialization for Deep
Transformers. ACL 2020.
- Herbig et al. MMPE: A Multi-Modal Interface for Post-Editing Machine
Translation. ACL 2020.
- Herbig et al. MMPE: A Multi-Modal Interface using Handwriting, Touch
Reordering and Speech Commands for Post-Editing Machine Translation. ACL
2020.
- Alabi et al. Massive vs. Curated Embeddings for Low-Resourced Languages:
the Case of Yor?b? and Twi. LREC 2020.
- Xu et al. Efficient Context-Aware Neural Machine Translation with
Layer-Wise Weighting and Input-Aware Gating. IJCAI 2020.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20201029/7bbfd184/attachment.html

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

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


End of Moses-support Digest, Vol 168, Issue 12
**********************************************

Tweet