EAMT 2012

Proceedings of the 16th Annual Conference of the

European Association for Machine Translation

Trento, Italy, May 28- 30 2012

Edited by

Mauro Cettolo, Marcello Federico, Lucia Specia, Andy Way

[complete proceedings]

Table of Contents

Foreword ............................................................................................................................................................................................................ IX

Message from the Conference Chair .................................................................................................................................................................... XI

Message from the Programme Chairs .................................................................................................................................................................. XIII

Committees ........................................................................................................................................................................................................ XV

Sponsors ........................................................................................................................................................................................................... XIX

Invited Talk:

The Unavoidable Adoption of Machine Translation .................................................................................................................................................. XXI

Donald A. DePalma

Oral Session 1 – User Papers

From Subtitles to Parallel Corpora ........................................................................................................................................................................... 3

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

Building English‐Chinese and Chinese‐English MT engines for the computer software domain ................................................................................. 7

M. Khalilov, R. Choudhury

Statistical Machine Translation prototype using UN parallel documents ..................................................................................................................... 12

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

User Evaluation of Interactive Machine Translation Systems ..................................................................................................................................... 20

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

Oral Session 2 – Research Papers

Translate, Predict or Generate: Modeling Rich Morphology in Statistical Machine Translation ........................................................................................ 27

A. El Kholy, N. Habash

Exploiting Shared Chinese Characters in Chinese Word Segmentation Optimization for Chinese‐Japanese Machine Translation …………………………... 35

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

Hebrew Morphological Preprocessing for Statistical Machine Translation ...................................................................................................................... 43

N. Singh, N. Habash

Poster Session 1 – User and Project Papers

User Papers:

Building Translation Awareness in Occasional Authors: A User Case from Japan .......................................................................................................... 53

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

Efficiency‐based evaluation of aligners for industrial applications ............................................................................................................................... 57

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

Evaluation of Machine‐Translated User Generated Content: A pilot study based on User Ratings .................................................................................. 61

L. Mitchell, J. Roturier

A Machine Translation Toolchain for Polysynthetic Languages ...................................................................................................................................... 65

P. Homola

EASTIN‐CL: A multilingual front‐end to a database of Assistive Technology products ................................................................................................. 69

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

Towards the Integration of MT into a LSP Translation Workflow ...................................................................................................................................... 73

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

Context‐Aware Machine Translation for Software Localization ....................................................................................................................................... 77

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

Project Papers:

Virtus™: Translation for Structured Data ......................................................................................................................................................................... 81

MOLTO ‐ Multilingual On‐Line Translation .................................................................................................................................................................. 82

AIDA: Automatic Identification and Glossing of Dialectal Arabic ........................................................................................................................................ 83

CESAR ‐ Central and South‐East European Resources ............................................................................................................................................... 84

BOLOGNA ‐ Bologna Translation Service....................................................................................................................................................................... 85

Poster Session 2 – Project Papers

ACCEPT ‐ Automated Community Content Editing PorTal ................................................................................................................................................ 89

PANACEA ‐ Platform for Automatic, Normalised Annotation and Cost‐Effective Acquisition of Language Resources for Human Language Technologies ....... 90

ATLAS ‐ Automatic Translation into Sign Languages ........................................................................................................................................................ 91

FAUST ‐ Feedback Analysis for User adaptive Statistical Translation ................................................................................................................................ 92

EU-BRIDGE ‐ Bridges Across the Language Divide .......................................................................................................................................................... 93

GF Eclipse Plugin: an IDE for grammar development in GF ................................................................................................................................................. 94

CrossLang Moses SMT Production System ....................................................................................................................................................................... 95

Embedding Machine Translation in ATLAS Content Management System ............................................................................................................................ 96

TTC ‐ Terminology Extraction, Translation Tools and Comparable Corpora ......................................................................................................................... 97

Confident MT ‐ Estimating Translation Quality for Improved Statistical Machine Translation ................................................................................................ 98

PET: a Tool for Post‐editing and Assessing Machine Translation ...................................................................................................................................... 99

LetsMT! ‐ Do‐It‐Yourself Machine Translation Factory on the Cloud ............................................................................................................................ 100

Oral Session 3 – Research Papers

Cross‐lingual Sentence Compression for Subtitles .......................................................................................................................................................... 103

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

Can Automatic Post‐Editing Make MT More Meaningful? ................................................................................................................................................ 111

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

Evaluating User Preferences in Machine Translation Using Conjoint Analysis ...................................................................................................................... 119

K. Kirchhoff, D. Capurro, A. Turner

Poster Session 3 – Research and Project Papers

Research Papers:

Cascaded Phrase‐Based Statistical Machine Translation Systems .................................................................................................................................. 129

D. Tufiş, S.D. Dumitrescu

Hybrid Parallel Sentence Mining from Comparable Corpora ................................................................................................................................................ 137

D. Ștefănescu, R. Ion, S. Hunsicker

Domain Adaptation of Statistical Machine Translation using Web‐Crawled Resources: A Case Study ................................................................................. 145

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

Relevance Ranking for Translated Texts .......................................................................................................................................................................... 153

M. Turchi, J. Steinberger, L. Specia

Automatic Tune Set Generation for Machine Translation with Limited Indomain Data ........................................................................................................... 161

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? ........................ 169

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

Long‐distance reordering during search for hierarchical phrase‐based SMT .................................................................................................................... 177

F. Braune, A. Gojun, A. Fraser

Mixture‐Modeling with Unsupervised Clusters for Domain Adaptation in Statistical Machine Translation ............................................................................... 185

R. Sennrich

Extending CCG‐based Syntactic Constraints in Hierarchical Phrase‐Based SMT ........................................................................................................... 193

H. Almaghout, J. Jiang, A. Way

Project Papers:

MosesCore ‐ Moses Open Source Evaluation and Support Co‐ordination for OutReach and Exploitation ........................................................................... 201

MateCat - Machine Translation Enhanced Computer Assisted Translation ........................................................................................................................... 202

SUMAT - An online service for SUbtitling by MAchine Translation ...................................................................................................................................... 203

TransLectures - Transcription and Translation of Video Lectures ........................................................................................................................................ 204

ACCURAT - Analysis and Evaluation of Comparable Corpora for Under Resourced Areas of Machine Translation ................................................................... 205

CoSyne - a Project on Multilingual Content Synchronization with Wikis ............................................................................................................................... 206

LT-Innovate - The Forum for Europe’s Language Technolgy Industry .................................................................................................................................. 207

TOSCA-MP – Task-oriented search and content annotation for media production ................................................................................................................ 208

Organic.Lingua - Demonstrating the Potential of a multilingual Web portal for Sustainable Agricultural & Environmental Education .......................................... 209

Poster Session 4 – Research Papers

Flexible finite-state lexical selection for rule-based machine translation ............................................................................................................................... 213

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

Statistical Post-Editing of Machine Translation for Domain Adaptation ................................................................................................................................ 221

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

Crowd-based MT Evaluation for non-English Target Languages .......................................................................................................................................... 229

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

Readability and Translatability Judgments for “Controlled Japanese” ................................................................................................................................... 237

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

A Phrase Table without Phrases: Rank Encoding for Better Phrase Table Compression ....................................................................................................... 245

M. Junczys‐Dowmunt

Creating Term and Lexicon Entries from Phrase Tables ..................................................................................................................................................... 253

G. Thurmair, V. Aleksić

WIT3: Web Inventory of Transcribed and Translated Talks ................................................................................................................................................ 261

M. Cettolo, C. Girardi, M. Federico

A Hybrid System for Patent Translation ........................................................................................................................................................................... 269

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

Oral Session 4 – Research Papers

Hierarchical Sub‐sentential Alignment with Anymalign .................................................................................................................................................... 279

A. Lardilleux, F. Yvon, Y. Lepage

Adjunct Alignment in Translation Data with an Application to Phrase Based Statistical Machine Translation .......................................................................... 287

S. Arnoult, K. Sima’an

LTG vs. ITG Coverage of Cross-Lingual Verb Frame Alternations ...................................................................................................................................... 295

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

Oral Session 5 – Research Papers

Learning Machine Translation from In-domain and Out-of-domain Data ............................................................................................................................... 305

M. Turchi, C. Goutte, N. Cristianini

Discriminative Reordering Extensions for Hierarchical Phrase-Based Machine Translation ................................................................................................... 313

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

Pivot-based Machine Translation between Statistical and Black Box systems .................................................................................................................... 321

A. Toral