Programme

 

Programme at a glance
Information about presentations
Detailed programme
Proceedings

 

Programme at a glance

Monday, May 28

  • 08:15-09:00 Registration
  • 09:00-09:20 Opening
  • 09:20-10:40 Oral 1 [User Studies]
  • 11:00-12:30 Oral 2 [Research]
  • 14:00-15:30 Poster 1 [User Studies, Projects]
  • 16:00-17:30 Poster 2 [Projects]
  • 17:30-18:15 EAMT business meeting
  • 19:00-20:30 Welcome Reception

Tuesday, May 29

Wednesday, May 30

  • 08:45-10:15 Oral 4 [Research]
  • 10:30-12:00 Oral 5 [Research]
  • 12:00-12:10 Closing remarks

 

Information about presentations

  • Oral presentations: talks on research track papers are allotted 25 minutes for presentation and 5 minutes for questions from the audience. Talks on user track papers are allotted 15 minutes for presentation and 5 minutes for questions. Please ensure that your presentation does not exceed the allotted length. Presentations must be uploaded on the conference computer before the session starts. The conference computer is equipped with Windows 7 OS, MS Office 2010, and Adobe Reader X 10.1; if you are not sure your PowerPoint presentation is properly handled by our Office version, please consider to convert it into PDF format.
  • Poster presentations: the size of the poster panel available to each presenter is about 1 meter (width) x 2 meters (height). Poster numbers will be assigned to each paper; material will  be provided by assistants. Short boaster sessions  are arranged (see detailed program below) for presenting posters of research and user papers: in 1 minute - without slides - try to convince people to come and see your work!

 

Detailed programme

Available here in pdf format.

 

Monday, May 28

 

08:15-09:00

Registration

 

09:00-09:20

Opening

 

09:20-10:40

Oral Session 1 – User Papers

 

09:20- 09:40

From Subtitles to Parallel Corpora

M. Fishel, Y. Georgakopoulou, S. Penkale, V. Petukhova, M. Rojc, M. Volk, A. Way

09:40-10:00

Building English-Chinese and Chinese-English MT engines for the computer software domain

M. Khalilov, R. Choudhury

10:00-10:20

Statistical Machine Translation prototype using UN parallel documents

B. Pouliquen, C. Mazenc, C. Elizalde, J. Garcia-Verdugo

10:20-10:40

User Evaluation of Interactive Machine Translation Systems

V. Alabau, L. A. Leiva, D. Ortiz-Martínez, F. Casacuberta

 

10:40-11:00

Coffee Break

 

11:00-12:30

Oral Session 2 – Research Papers

 

11:00-11:30

Translate, Predict or Generate: Modeling Rich Morphology in Statistical Machine Translation

A. El Kholy, N. Habash

11:30-12:00

Exploiting Shared Chinese Characters in Chinese Word Segmentation Optimization for Chinese-Japanese Machine Translation

C. Chu, T. Nakazawa, D. Kawahara, S. Kurohashi

12:00-12:30

Hebrew Morphological Preprocessing for Statistical Machine Translation

N. Singh, N. Habash

 

12:30-12:40

Poster boaster (1 minute each) – User Papers of Poster Session 1

 

12:40-14:00

Lunch

 

14:00-15:30

Poster Session 1 – User and Project Papers

 

User Papers:

·      Building Translation Awareness in Occasional Authors: A User Case from Japan

M. Tatsumi, A. Hartley, H. Isahara, K. Kageura, T. Okamoto, K. Shimizu

·      Efficiency-based evaluation of aligners for industrial applications

A. Toral, M. Poch, P. Pecina, G. Thurmair

·      Evaluation of Machine-Translated User Generated Content: A pilot study based on User Ratings

L. Mitchell, J. Roturier

·      A Machine Translation Toolchain for Polysynthetic Languages

P. Homola

·      EASTIN-CL: A multilingual front-end to a database of Assistive Technology products

G. Thurmair, A. Agnoletto, V. Gower, R. Rozis

·      Towards the Integration of MT into a LSP Translation Workflow

D. Vilar, M. Schneider, A. Burchardt,  T. Wedde

·      Context-Aware Machine Translation for Software Localization

V. Muntés-Mulero, P. Paladini Adell, C. España-Bonet, L. Màrquez

 

Project Papers:

·      Virtus™: Translation for Structured Data

·      MOLTO - Multilingual On-Line Translation

·      AIDA: Automatic Identification and Glossing of Dialectal Arabic

·      CESAR - Central and South-East European Resources

·      BOLOGNA - Bologna Translation Service

 

15:30-16:00

Coffee break

 

16:00-17:30

Poster Session 2 – Project Papers

 

·      ACCEPT - Automated Community Content Editing PorTal

·      PANACEA - Platform for Automatic, Normalised Annotation and Cost-Effective Acquisition of Language Resources for Human Language Technologies

·      ATLAS - Automatic Translation into Sign Languages

·      FAUST - Feedback Analysis for User adaptive Statistical Translation

·      EU-BRIDGE - Bridges Across the Language Divide

·      GF Eclipse Plugin: an IDE for grammar development in GF

·      CrossLang Moses SMT Production System

·      Embedding Machine Translation in ATLAS Content Management System

·      TTC - Terminology Extraction, Translation Tools and Comparable Corpora   

·      Confident MT - Estimating Translation Quality for Improved Statistical Machine Translation

·      PET: a Tool for Post-editing and Assessing Machine Translation

·      LetsMT! - Do-It-Yourself Machine Translation Factory on the Cloud

 

17:30-18:15

EAMT Business meeting

 

18:15 Closure

 

19:00-20:30

           Welcome Reception

 

Tuesday, May 29

 

09:00-09:30

Best EAMT thesis: Stream-based Statistical Machine Translation

Abby Levenberg

 

09:30-10:30

Invited Talk:  The Unavoidable Adoption of Machine Translation

Donald A. DePalma

Chief Strategy Officer and Founder of Common Sense Advisory, Inc.

 

10:30-10:50

Coffee break

 

10:50-12:20

Oral Session 3 – Research Papers

 

10:50-11:20

Cross-lingual Sentence Compression for Subtitles

W. Aziz, S. C. M. de Sousa, L. Specia

11:20-11:50

Can Automatic Post-Editing Make MT More Meaningful?

K. Parton, N. Habash, K. McKeown, G. Iglesias, A. de Gispert

11:50-12:20

Evaluating User Preferences in Machine Translation Using Conjoint Analysis

K. Kirchhoff, D. Capurro, A. Turner

 

 

12:20-12:30

Poster boaster (1 minute each) – Research Papers of Poster Session 3

 

12:30-14:00

Lunch

 

14:00-15:30

Poster Session 3 – Research and Project Papers

 

Research Papers:

·      Cascaded Phrase-Based Statistical Machine Translation Systems

D. Tufiş,  S.D. Dumitrescu

·      Hybrid Parallel Sentence Mining from Comparable Corpora

D. Ștefănescu, R. Ion, S. Hunsicker

·      Domain Adaptation of Statistical Machine Translation using Web-Crawled Resources: A Case Study

P. Pecina, A. Toral, V. Papavassiliou, P. Prokopidis, J. van Genabith

·      Relevance Ranking for Translated Texts

M. Turchi, J. Steinberger, L. Specia

·      Automatic Tune Set Generation for Machine Translation with Limited In-domain Data

J. Chen, J. Devlin, H. Cao, R. Prasad, P. Natarajan

·      Domain Adaptation in SMT of User-Generated Forum Content Guided by OOV Word Reduction: Normalization and/or Supplementary Data?

P. Banerjee, S. K. Naskar, J. Roturier, A. Way, J. van Genabith

·      Long-distance reordering during search for hierarchical phrase-based SMT

F. Braune, A. Gojun, A. Fraser

·      Mixture-Modeling with Unsupervised Clusters for Domain Adaptation in Statistical Machine Translation

R. Sennrich

·      Extending CCG-based Syntactic Constraints in Hierarchical Phrase-Based SMT

H. Almaghout, J. Jiang, A. Way

 

Project Papers:

·      MosesCore - Moses Open Source Evaluation and Support Co-ordination for OutReach and Exploitation

·      MateCat - Machine Translation Enhanced Computer Assisted Translation

·      SUMAT - An online service for SUbtitling by MAchine Translation

·      transLectures - Transcription and Translation of Video Lectures

·      ACCURAT - Analysis and Evaluation of Comparable Corpora for Under Resourced Areas of Machine Translation

·      CoSyne - a Project on Multilingual Content Synchronization with Wikis

·      LT-Innovate - The Forum for Europe's Language Technology Industry

·      TOSCA-MP - Task-oriented search and content annotation for media production

·      Organic.Lingua - Demonstrating the Potential of a multilingual Web portal for Sustainable Agricultural & Environmental Education

 

15:30-15:50

Coffee break

 

15:50-16:00

Poster boaster (1 minute each) – Research Papers of Poster Session 4

 

16:00-17:30

Poster Session 4 – Research Papers

 

·      Flexible finite-state lexical selection for rule-based machine translation

F. M. Tyers, F. Sánchez-Martínez, M. L. Forcada

·      Statistical Post-Editing of Machine Translation for Domain Adaptation

R. Rubino, S. Huet, F. Lefèvre, G. Linarès

·      Crowd-based MT Evaluation for non-English Target Languages

M. Paul, E. Sumita, L. Bentivogli, M. Federico

·      Readability and Translatability Judgments for “Controlled Japanese”

A. Hartley, M. Tatsumi, H. Isahara, K. Kageura, R. Miyata

·      A Phrase Table without Phrases: Rank Encoding for Better Phrase Table Compression

M. Junczys-Dowmunt

·      Creating Term and Lexicon Entries from Phrase Tables

G. Thurmair, V. Aleksić

·      WIT3: Web Inventory of Transcribed and Translated Talks

M. Cettolo, C. Girardi, M. Federico

·      A Hybrid System for Patent Translation

R. Enache, C. España-Bonet, A. Ranta, L. Màrquez

 

 

 

17:30 Closure

18:00 Social dinner 

   Best paper award: Can  Automatic Post-Editing Make MT More Meaningful?

    K. Parton, N. Habash, K. McKeown, G. Iglesias, A. de Gispert

 

Wednesday, May 30

 

08:45-10:15

Oral Session 4 – Research Papers

 

08:45-09:15

Hierarchical Sub-sentential Alignment with Anymalign

A. Lardilleux, F. Yvon, Y. Lepage

09:15-09:45

Adjunct Alignment in Translation Data with an Application to Phrase-Based Statistical Machine Translation

S. Arnoult, K. Sima’an

09:45-10:15

LTG vs. ITG Coverage of Cross-Lingual Verb Frame Alternations

K. Addanki, C. Lo, M. Saers, D. Wu

 

10:15-10:30

Coffee break

 

10:30-12:00

Oral Session 5 – Research Papers

 

10:30-11:00

Learning Machine Translation from In-domain and Out-of-domain Data

M. Turchi, C. Goutte, N. Cristianini

11:00-11:30

Discriminative Reordering Extensions for Hierarchical Phrase-Based Machine Translation

M. Huck, S. Peitz, M. Freitag, H. Ney

11:30-12:00

Pivot-based Machine Translation between Statistical and Black Box systems

A. Toral

 

12:00-12:10

Closing Remarks

 

12:00-14:00

Lunch