October 28:

— Introduction to MT (Jay Marciano)

Dependency-Based Statistical Machine Translation (Qun Liu and Liangyou Li)

November 1:

Computer Aided Translation: Advances and Challenges (Philipp Koehn)

Advances in Neural Machine Translation (Rico Sennrich, Alexandra Birch, and Marcin Junczys-Dowmunt)

ModernMT (Marcello Federico and Marco Trombetti)

 

Scroll down for more information.


 

 

Introduction to MT        October 28, Morning

This tutorial is for people who are beginning their journey with machine translation and want an overview of what it is, how it works, how it can be used, and whether it can fulfil their needs. No previous knowledge of machine translation is assumed, and all levels of skepticism are welcome. The focus will be on providing background knowledge that will help you get more out of the rest of the AMTA conference and make more informed decisions about how to use or invest in machine translation. Past participants have ranged from translation professionals who want to understand changes in their field to corporate executives who are evaluating technology strategies for their organizations. The main topics for discussion are common questions about MT (What is MT and how does it differ from other translation technologies? How well can machines really translate? What are the latest trends in MT research and development?), the quality of the translations it produces (Why is the output sometimes so bad? How can the quality be improved? Can translation quality be measured objectively?), and its application (What is MT good for? Have we reached the point of Star Trek’s universal translator? Will we? Can MT improve a translator’s efficiency? What are the implications of this technology for translators?). You will leave this tutorial with the tools you need to take part in an informed discussion of MT.

Presenter: Jay Marciano

 

Dependency-Based Statistical Machine Translation        October 28, Afternoon

Syntax-based translation models learn translation patterns from recursive structures over sentences. Compared to phrase-based models (Koehn et al., 2003) they have a better capability of long-distance reordering and generalization, especially for MT between distant languages. Constituent structures have been widely used in statistical machine translation (SMT), but translation models built on constituent structures are computationally complex and inefficient when multi-level rules are taken into consideration. By contrast, dependency structures do not attract enough attention in SMT, although dependency grammar is regarded to be very helpful because it directly encodes semantic information and has the best inter-lingual phrasal cohesion properties (Fox, 2002).
In this tutorial, we will introduce representative work on dependency-based SMT, including:

  • — Translation models based on segmentation:
      o Dependency treelet models
      o Dependency graph segmentation models
  • — Translation models based on synchronous grammars:
      o String-to-dependency models
      o Dependency-to-string models
      o Dependency-graph-to-string models
  • — Dependency-based evaluation
  • — Lab session with our open source tools

Presenters: Qun Liu and Liangyou Li

 

Computer Aided Translation: Advances and Challenges        November 1, Morning

Moving beyond post-editing machine translation, a number of recent research efforts have advanced computer aided translation methods that allow for more interactivity, richer information such as confidence scores, and the completed feedback loop of instant adaptation of machine translation models to user translations. This tutorial will explain the main techniques for several aspects of computer aided translation:
– confidence measures
– interactive machine translation (interactive translation prediction)
– bilingual concordancers
– translation option display
– online adaptation
– eye tracking, logging, and cognitive user models
For each of these, the state of the art and open challenges are presented.
The tutorial will also look under the hood of the open source CASMACAT toolkit that is based on MATECAT, and available as a “Home Edition” to be installed on a desktop machine. The target audience of this tutorial are researchers interested in computer aided machine translation and practitioners who want to use or deploy advanced CAT technology.

Presenter: Philipp Koehn

 

Advances in Neural Machine Translation        November 1, Afternoon

Neural machine translation has been introduced to the field of natural language processing and machine translation. Unlike existing approaches to machine translation, neural machine translation tackles the problem of translation by directly modelling the conditional probability of a translation given a source sentence without any assumption on factorization. Already in two years, neural machine translation has proven itself to be competitive against the existing translation approaches in many language pairs, which has excited many researchers in the field. In the first part of this tutorial, I will give an introduction to neural machine translation together with basics in connectionist natural language processing. This will be followed by describing new opportunities in machine translation that have become possible by introducing deep learning to machine translation. These opportunities include sub-word/character-level translation, multilingual translation and simultaneous machine translation.

Presenters: Rico Sennrich, Alexandra Birch, and Marcin Junczys-Dowmunt

 

ModernMT        November 1, Afternoon

The ModernMT project aims at making a contribution to the evolution of machine translation. Our goal is to consolidate the current state­ of ­the ­art technology into a single easy-to-­use product, evolving it and keeping it open to integrate the next greatest opportunities in machine intelligence, like deep learning.

In particular, we will introduce and demonstrate the ModernMT system architecture, whose distinguishing features make it particularly useful to be integrated in the Computer-Assisted Translation framework, namely its capability to (i) adapt in real time to the document to be translated and (ii) quickly learn from data provided by the users, such as translation memories and post-edited data. The MMT architecture builds on open source software (Moses, Lucene, etc.) and comes as a-ready-to-install application, that does not require any initial training phase and that enables scalability of data and users.

Our tutorial will cover the following aspects of the ModernMT project:

  •   — Introduction: main features and development roadmap
  •   — Development: software architecture and components
  •   — Field testing: ongoing testing activities with the industry and results
  •   — Integration: deployment and integration of ModernMT in CAT tools
  •   — Hands ­on session: participants will learn how to install, start, and use ModernMT

Presenters: Marcello Federico and Marco Trombetti

Contact: Jay Marciano (tutorials@amtaweb.org)

MT Summit XV is seeking proposals for tutorials on all topics related to MT. We are interested in tutorials from experts in the following areas:

However, any themes connected to MT research, development, deployment, use, and evaluation are welcome.

Tutorials will be held on Friday, 30 October 2015, immediately preceding the main conference, or Tuesday, 3 November 2015, immediately following the main conference.

Aims

Tutorials at the MT Summit are a forum for experts in MT and MT-related areas to deliver concentrated training on a topic of interest in half-day (or occasionally full-day) teaching sessions. Tutorials provide background that helps conference participants (especially newcomers to the field) understand the conference program, and/or enrich their understanding of particular technical, applied, and business matters surrounding research, development and use of MT and translation technology. Tutorials are often delivered as presentations, sometimes with demos, online information, participant exercises and other instructional materials and activities.

Compensation

The tutorial presenter will receive an honorarium of $500 if there are at least 12 registered attendees for the tutorial. The honorarium will not increase if there is more than one presenter. Please note that for cost reasons, the MT Summit XV organizing committee reserves the right, at its discretion, to cancel any tutorial that has fewer than 8 to 10 registered attendees.

Tutorial materials

The tutorial fees reflect the fact that participants are getting access to an expert, and gaining something of value. It is important to provide well-organized handouts and other materials for the participants. Tutorial speakers are responsible for providing materials such as presentation slides, and other materials that form part of the tutorial (all in PDF format) to AMTA so that tutorial registrants can access the materials online before the tutorial session and if they wish, to print them out and bring it along with them to AMTA 2014. Tutorial speakers have to provide these materials to the Tutorials chair on or before the tutorial materials due date.

How to submit a tutorial proposal

Visit the following link to submit your proposal: MT_Summit_XV_Tutorial_Proposal_Form

After you have submitted your proposal, you can continue to edit your proposal submission until the submission deadline.

If you have any questions about the Tutorials proposal submission process then please contact the MT
Summit XV Tutorials Chair: Jay Marciano (tutorials@amtaweb.org) with the subject line: “MT Summit XV tutorial proposal”.

Important dates:

CAT Tool Workshop        October 28

This workshop is intended for translators who are curious about machine translation but have never seriously experimented with it or tried their hand at post-editing. The workshop will invite a limited number of CAT tool vendors whose systems incorporate machine translation and allow each forty minutes to demonstrate their system’s MT features, particularly those designed for post-editing. We will select vendors whose systems cover a range of different options, in terms of the type of embedded MT technology, language pairs covered, retraining options, licencing and software delivery model, facilities offered for post-editing, etc. We will also encourage the vendors to give workshop attendees the chance to actively try out their system using their own texts.
Organizer: Elliott Macklovitch

 

Workshop on Interacting with Machine Translation (iMT)        October 28

This workshop will consider questions relating to various forms of human interaction with MT, such as: How do organizations currently measure end-user interaction and satisfaction with MT? How does raw or post-edited MT affect usability of products or content? How does translator interaction with MT differ from translator interaction with human translation? How can MT developers best use end-user interaction data to improve MT output quality and user experience of MT? The term interacting is deliberately used to broaden the focus beyond post-editing and interactive MT, though both of these topics fit comfortably within the theme. The workshop will feature invited talks by prominent researchers in the field, as well as oral presentations of ongoing research work. Presentations will be selected based on submitted extended (500-word) abstracts. Presenting researchers will be invited to submit a paper to a special issue of Machine Translation journal on this topic.
Organizers: Sharon O’Brien, Michel Simard

 

Assessing Translation Quality Metrics        October 28

Assessing the quality of production translation has become a key concern for translation consumers and end users, for translators and language service companies, and for researchers seeking to compare or improve tools, particularly machine translation. There are currently three standards in development in ASTM’s Language Services Committee and two standards in ISO’s Technical Committee 37 on Terminology and Other Language and Content Resources that focus on assessing translation quality. The Translation Automation Users Society (TAUS) has created a Quality Dashboard and framework (i.e., the Dynamic Quality Framework, now merged with the Multidimensional Quality Framework) which is extensively influencing some of the standards efforts.

This workshop reviews the types of questions asked by customers and end users of translation and by Language Service Providers. It then addresses the types of metrics and assessment methods currently available, looking at how effectively and under what conditions the assessment meets both the metric and the user or provider questions. The workshop then generates recommendations for ASTM, ISO, and TAUS, and for providers and consumers of translation, and for researchers and developers.
Organizer: Jennifer DeCamp (MITRE)

 

Workshop on MT for Semitic Languages        November 1

Semitic languages are used by a significantly large population of native speakers and belong to a family that includes classical Arabic, a large number of Arabic dialects, Hebrew, Amharic, Maltese and other languages. These languages are characterized by a system of word formation based on roots and patterns, a rich and productive morphology (including non-concatenative processes), a diversity of orthographic conventions and, unfortunately, limited language resources suitable for computational research and development.

Semitic languages as a whole are still understudied, although over the past decade there has been a body of computational processing research specifically targeted to individual Semitic languages, much of the work to date remains the result of initiatives undertaken by individual researchers or research establishments. Several workshops in recent years – both regional and affiliated with international conferences – have addressed the spectrum of issues relating to the processing of Arabic, Hebrew and other Semitic languages. The progress of recent years has opened the door to advanced computational applications such as machine translation. Research on machine translation of Semitic languages is, however, still in its early stages. Accurate translation of Arabic, Hebrew, Amharic, Maltese and other Semitic languages requires treatment of unique linguistic characteristics, some of which are common to all Semitic languages, others specific to each of these individual languages and their dialects.

The goal of this workshop is to bring together researchers and research specifically concerned with issues pertaining to machine translation to, from, and among Semitic languages. Furthermore, the workshop will be an opportunity for the Special Interest Group on Computational Approaches to Semitic Languages (the SIG) to meet and discuss future direction in Computational Linguistics and Natural Language Processing approaches to Semitic Languages.

Organizers: Mona Diab, GWU, USA; Houda Bouamor, CMU-Qatar; Ahmed ElKholy, Microsoft, USA; Mahmoud Ghoneim, GWU, USA; Yuval Marton, Microsoft, USA

 

Contact: Jen Doyon (governmentmtusers@amtaweb.org)

Government users are encouraged to contribute to MT Summit 2015 by submitting proposals for this year’s conference that pertain to the research, development and operational use of MT and MT-related technologies in government settings.

Important dates:

Topics of interest include but are not limited to the following:

What to submit:

Submissions should be 250-500 word abstracts.  The following should accompany each abstract submission:

All accepted submissions will be allotted 30 minute time slots.  While not mandatory, presenters wishing to have their submissions published in the MT Summit Proceedings are required to produce papers in accordance with the MT Research Track Submission Instructions found in the Call for MT Research Papers.  Presenters are advised to obtain the broadest level of release of their presentations and papers in their approval/release process in order to facilitate sharing and distribution.

If you have original software that you would like to show, you may also consider submitting a proposal for the MT Summit technology showcase.  See the “Call for MT Technology Demonstrations and Exhibits” on the conference website. [Coming soon.]

How to submit:

Please email your abstract to the Government MT Users Chair (governmentmtusers@amtaweb.org) by Monday, July 13, 2015.

The Program Committee of MT Summit XVI has extended the submission deadlines of two tracks:

– Submissions to the Research track can be submitted until June 5th (three weeks extension). See more details here.
– Submissions to the Commercial MT Users and Translators track can be submitted until June 12th (11 days extension). See more details here.

 Main Conference

Proceedings of AMTA 2016, vol. 1:  MT Researchers’ Track   Spence Green and Lane Schwartz (Eds.)

Proceedings of AMTA 2016, vol. 2:  MT Users’ Track   Olga Beregovaya, Jennifer Doyon, Lucie Langlois, and Steve Richardson (Eds.)

MT Marathons, Open Source, and Collaborative Research in MT   Phillip Koehn, Research Track Invited Talk

 

Keynotes

MT escaped from the Lab. Now what?   Mike Dillinger
Interactive Machine Translation: From Research to Practice Spence Green
DARPA Human Language Technology Programs   Doug Jones
Neural MT: Breaking the Performance Plateau Rico Sennrich

 

Tutorials

Dependency-based Statistical MT   Qun Liu & Liangyou Li

Computer Aided Translation: Advances and Challenges   Philipp Koehn

Advances in Neural Machine Translation   Rico Sennrich, Alexandra Birch, and Marcin Junczys-Dowmunt

ModernMT   Marcello Federico and Marco Trombetti

 

Workshops

CAT Tool Workshop: Star Transit Presentation

New Tutorials for AMTA 2016

by Darius Hughes | June 12, 2017

October 28: — Introduction to MT (Jay Marciano) — Dependency-Based Statistical Machine Translation (Qun Liu and Liangyou Li) November 1: — Computer Aided Translation: Advances and Challenges (Philipp Koehn) — Advances in Neural Machine Translation (Rico Sennrich, Alexandra Birch, and Marcin Junczys-Dowmunt) — ModernMT (Marcello Federico and Marco Trombetti)   Scroll down for more information. […]

Archieve Read more...

MT Summit XV | Call for Tutorial Proposals

by Darius Hughes | June 12, 2017

Contact: Jay Marciano (tutorials@amtaweb.org) MT Summit XV is seeking proposals for tutorials on all topics related to MT. We are interested in tutorials from experts in the following areas: MT Researchers and developers Commercial MT Users Government MT Users, and Translators using MT However, any themes connected to MT research, development, deployment, use, and evaluation […]

Archieve Read more...

AMTA 2016 | Accepted Workshops

by Darius Hughes | March 23, 2017

CAT Tool Workshop        October 28 This workshop is intended for translators who are curious about machine translation but have never seriously experimented with it or tried their hand at post-editing. The workshop will invite a limited number of CAT tool vendors whose systems incorporate machine translation and allow each forty minutes to demonstrate their […]

Archieve Read more...

MT Summit XV | Government MT Users: Call for Presentations

by Darius Hughes | March 13, 2017

Contact: Jen Doyon (governmentmtusers@amtaweb.org) Government users are encouraged to contribute to MT Summit 2015 by submitting proposals for this year’s conference that pertain to the research, development and operational use of MT and MT-related technologies in government settings. Important dates: Submission deadline: Monday July 13 Notifications of acceptance: Monday August 27 Final “camera-ready” versions: Monday […]

Archieve Read more...

MT Summit XVI | CFP and Extended Deadlines!

by Darius Hughes | January 29, 2017

The Program Committee of MT Summit XVI has extended the submission deadlines of two tracks: – Submissions to the Research track can be submitted until June 5th (three weeks extension). See more details here. – Submissions to the Commercial MT Users and Translators track can be submitted until June 12th (11 days extension). See more […]

Archieve Read more...

AMTA 2016 | Proceedings are available

by Darius Hughes | October 29, 2016

 Main Conference Proceedings of AMTA 2016, vol. 1:  MT Researchers’ Track   Spence Green and Lane Schwartz (Eds.) Proceedings of AMTA 2016, vol. 2:  MT Users’ Track   Olga Beregovaya, Jennifer Doyon, Lucie Langlois, and Steve Richardson (Eds.) MT Marathons, Open Source, and Collaborative Research in MT   Phillip Koehn, Research Track Invited Talk   Keynotes MT escaped […]

Archieve Read more...