Workshop on Technologies for MT of Low Resource Languages (LoResMT)
Boston, Massachusetts, March 21, 2018
https://sites.google.com/view/loresmt-2018/
@ AMTA 2018 (http://www.conference.amtaweb.org/)
NEWS
- Link to the current LoResMT workshop website.https://sites.google.com/view/loresmt/
- LoResMT 2018 Slides on-line! Please find below.
- Apertium paper slides are available online.https://jonorthwash.github.io/2018-ApertiumWeb-slides/
- March 22, 2018: Proceeding of LoResMT 2018 Workshop Onlinehttps://amtaweb.org/amta-2018-proceedings-for-the-conference-workshops-and-tutorials/
- March 5, 2018: Program Available
Updates and Errata of the Proceeding.
1. On the Contents Page, the starting page ofSystem Description of Supervised and Unsupervised Neural Machine Translation Approachesfrom “NL Processing” Team at DeepHack.Babel Taskis 45 (rather than 81).
2. On Page 62, the following linkshttps://github.com/goavki/apertium-html-toolshttps://github.com/goavki/apertium-apyare updated ashttps://github.com/apertium/apertium-html-toolshttps://github.com/apertium/apertium-apyrespectively.
- Link to the current LoResMT workshop website.https://sites.google.com/view/loresmt/
- LoResMT 2018 Slides on-line! Please find below.
- Apertium paper slides are available online.https://jonorthwash.github.io/2018-ApertiumWeb-slides/
- March 22, 2018: Proceeding of LoResMT 2018 Workshop Onlinehttps://amtaweb.org/amta-2018-proceedings-for-the-conference-workshops-and-tutorials/
- March 5, 2018: Program Available
Updates and Errata of the Proceeding.
1. On the Contents Page, the starting page ofSystem Description of Supervised and Unsupervised Neural Machine Translation Approachesfrom “NL Processing” Team at DeepHack.Babel Taskis 45 (rather than 81).
2. On Page 62, the following linkshttps://github.com/goavki/apertium-html-toolshttps://github.com/goavki/apertium-apyare updated ashttps://github.com/apertium/apertium-html-toolshttps://github.com/apertium/apertium-apyrespectively.
SCOPES
Statistical and neural machine translation (SMT/NMT) methods have been successfully used to build MT systems in many popular languages in the last two decades with significant improvements on the quality of automatic translation. However, these methods still rely upon a few natural language processing (NLP) tools to help pre-process human generated texts in the forms that are required as input for these methods, and/or post-process the output in proper textual forms in target languages.
In many MT systems, the performance of these tools has great impacts on the quality of resulting translation. However, there is not much discussion on these NLP tools, their methods, their roles in different MT systems of diverse methods, and their coverage of support in the many languages of the world, etc. In this workshop, we would like to bring together researchers who work on these topics and help review/overview what are the most important tasks we need from these tools for MT in the following years.
These NLP tools include, but not limited to, several kinds of word tokenizers/de-tokenizers, word segmenters, morphology analysers, etc. In this workshop, we solicit papers dedicated to these supplementary tools that are used in any language and especially in low resource languages. We would like to have an overview of these NLP tools from our community. The evaluations of these tools in research papers should include how they have improved the quality of MT output. The workshop also solicits papers working on MT systems/methods for low resource languages in general. The scopes of the workshop are not limited to the NLP tools for MT pre-processing and post-processing.
Statistical and neural machine translation (SMT/NMT) methods have been successfully used to build MT systems in many popular languages in the last two decades with significant improvements on the quality of automatic translation. However, these methods still rely upon a few natural language processing (NLP) tools to help pre-process human generated texts in the forms that are required as input for these methods, and/or post-process the output in proper textual forms in target languages.
In many MT systems, the performance of these tools has great impacts on the quality of resulting translation. However, there is not much discussion on these NLP tools, their methods, their roles in different MT systems of diverse methods, and their coverage of support in the many languages of the world, etc. In this workshop, we would like to bring together researchers who work on these topics and help review/overview what are the most important tasks we need from these tools for MT in the following years.
These NLP tools include, but not limited to, several kinds of word tokenizers/de-tokenizers, word segmenters, morphology analysers, etc. In this workshop, we solicit papers dedicated to these supplementary tools that are used in any language and especially in low resource languages. We would like to have an overview of these NLP tools from our community. The evaluations of these tools in research papers should include how they have improved the quality of MT output. The workshop also solicits papers working on MT systems/methods for low resource languages in general. The scopes of the workshop are not limited to the NLP tools for MT pre-processing and post-processing.
TOPICS
We solicit original research papers, review papers as well as position papers on these tools in the workshop. Multilingual and/or Cross-lingual NLP tools for MT of low resource languages are especially welcome. Topics of the workshop include but not limited to
- Research and review papers of pre-process and/or post-process NLP tools for MT- Position papers on the development of pre-process and/or post-process tools for MT- Word tokenizers/de-tokenizers for specific languages- Word/morpheme segmenters for specific languages- Alignment/Re-ordering tools for specific language-pairs- Use of morphology analysers and/or morpheme segmenters for MT- Multilingual and/or Cross-lingual NLP tools for MT- Reusability of existing NLP tools for low resource languages- Corpora curation technologies for low resource languages- Review of available parallel corpora for low resource languages- Research and review papers of MT methods for low resource languages- MT systems/methods (e.g. rule-based, PBMT, NMT) for low resource languages- Fast building of MT systems for low resource languages- Reusability of existing MT systems for low resource languages
We solicit original research papers, review papers as well as position papers on these tools in the workshop. Multilingual and/or Cross-lingual NLP tools for MT of low resource languages are especially welcome. Topics of the workshop include but not limited to
- Research and review papers of pre-process and/or post-process NLP tools for MT- Position papers on the development of pre-process and/or post-process tools for MT- Word tokenizers/de-tokenizers for specific languages- Word/morpheme segmenters for specific languages- Alignment/Re-ordering tools for specific language-pairs- Use of morphology analysers and/or morpheme segmenters for MT- Multilingual and/or Cross-lingual NLP tools for MT- Reusability of existing NLP tools for low resource languages- Corpora curation technologies for low resource languages- Review of available parallel corpora for low resource languages- Research and review papers of MT methods for low resource languages- MT systems/methods (e.g. rule-based, PBMT, NMT) for low resource languages- Fast building of MT systems for low resource languages- Reusability of existing MT systems for low resource languages
SUBMISSION INFORMATION
Workshop papers should follow AMTA 2018 style guide (PDF, LaTeX, Word).
There are two types of submissions in the workshop. For research, review and position papers, the length of each paper should be at least four (4) and not exceed eight (8) pages, plus additional two (2) pages for references. More pages would be allowed as long as it could be justified. The review will be double-blind. For non-archival system demonstration abstracts, the length should be two (2) or more pages. The review will be single-blind.
We would like to encourage authors to cite papers written in ANY language that are related to the topic they are working on, as long as both original bibliographic items and their corresponding English translations are given.
The submission website is online already. Submission deadline is February 4, 2018 anywhere in the world.https://www.softconf.com/amta2018/loresmt/
Workshop papers should follow AMTA 2018 style guide (PDF, LaTeX, Word).
There are two types of submissions in the workshop. For research, review and position papers, the length of each paper should be at least four (4) and not exceed eight (8) pages, plus additional two (2) pages for references. More pages would be allowed as long as it could be justified. The review will be double-blind. For non-archival system demonstration abstracts, the length should be two (2) or more pages. The review will be single-blind.
We would like to encourage authors to cite papers written in ANY language that are related to the topic they are working on, as long as both original bibliographic items and their corresponding English translations are given.
The submission website is online already. Submission deadline is February 4, 2018 anywhere in the world.https://www.softconf.com/amta2018/loresmt/
IMPORTANT DATES
December 22, 2017: First call for papers January 10, 2018: Second call for papers February 12, 2018 (Extended): Submission deadline of workshop papers February 19, 2018: Notification of acceptance February 24, 2018: Camera-ready papers due March 21, 2018: LoResMT workshop
ORGANIZERS
Alina Karakanta Universität des Saarlandes Chao-Hong Liu ADAPT Centre, Dublin City University Daria Dzendzik ADAPT Centre, Dublin City University Erlyn Manguilimotan Weathernews Inc., Japan, formerly with NAIST Francis Tyers Higher School of Economics, National Research University Iacer Calixto ADAPT Centre, Dublin City University Ian Soboroff National Institute of Standards and Technology (NIST) Jonathan Washington Swarthmore College Majid Latifi Universitat Politècnica de Catalunya Nathaniel Oco National University (Philippines) Peyman Passban ADAPT Centre, Dublin City University Prachya Boonkwan National Electronics and Computer Technology Center Sangjie Duanzhu Qinghai Normal University Santanu Pal Universität des Saarlandes Sivaji Bandyopadhyay Jadavpur University Sudip Kumar Naskar Jadavpur University Thepchai Supnithi National Electronics and Computer Technology Center Tommi A Pirinen Universität Hamburg Valentin Malykh Moscow Institute of Physics and Technology Vinit Ravishankar Charles University in Prague Yalemisew Abgaz ADAPT Centre, Dublin City University
Alina Karakanta Universität des Saarlandes Chao-Hong Liu ADAPT Centre, Dublin City University Daria Dzendzik ADAPT Centre, Dublin City University Erlyn Manguilimotan Weathernews Inc., Japan, formerly with NAIST Francis Tyers Higher School of Economics, National Research University Iacer Calixto ADAPT Centre, Dublin City University Ian Soboroff National Institute of Standards and Technology (NIST) Jonathan Washington Swarthmore College Majid Latifi Universitat Politècnica de Catalunya Nathaniel Oco National University (Philippines) Peyman Passban ADAPT Centre, Dublin City University Prachya Boonkwan National Electronics and Computer Technology Center Sangjie Duanzhu Qinghai Normal University Santanu Pal Universität des Saarlandes Sivaji Bandyopadhyay Jadavpur University Sudip Kumar Naskar Jadavpur University Thepchai Supnithi National Electronics and Computer Technology Center Tommi A Pirinen Universität Hamburg Valentin Malykh Moscow Institute of Physics and Technology Vinit Ravishankar Charles University in Prague Yalemisew Abgaz ADAPT Centre, Dublin City University
CONTACT
chaohong.liu@adaptcentre.ie
chaohong.liu@adaptcentre.ie