AMTA 2012
Proceedings of the Tenth Conference of the
Association for Machine Translation in the
Alon Lavie
Conference Chair
George Foster,
Mike Dillinger, Ray Flournoy,
Nick Bemish, Chuck Simmons
Program Chairs
October 28 – November 1, 2012
Table of Contents
Keynote Presentations
Domain Adaptation in Machine Translation:
Findings from the 2012 Johns Hopkins Summer Workshop
Hal Daumé, III, University of Maryland;
Marine Carpuat, National Research Council, Canada; Alex Fraser, University of Stuttgart; Chris Quirk, Microsoft Research
Trends in
Adoption of MT as a Globalization Technology
Don DePalma, Chief Strategy Officer &
Founder, Common Sense Advisory
Language Research
at DARPA-Machine Translation and Beyond
Bonnie J. Dorr, Professor,
Duolingo:
Learn a Language for Free while Helping to Translate the Web
Luis von Ahn, Associate
Professor,
Caitilin Walsh,
President-Elect, American Translators Association (ATA)
MT Research Papers
Oral Presentations
Hierarchical Phrase-Based MT for Phonetic
Representation-Based Speech Translation
Zeeshan Ahmed, Jie Jiang,
Julie Carson-Berndsen, Peter Cahill &
Identifying Infrequent Translations by
Aligning Non Parallel Sentences
Julien Bourdaillet &
Philippe Langlais
Sample
Selection for Large-scale MT Discriminative Training
Yuan Cao & Sanjeev
Khudanpur
One System, Many Domains: Open-Domain Statistical
Machine Translation via Feature Augmentation
Jonathan Clark, Alon Lavie
& Chris Dyer
Identification
of Fertile Translations in Comparable Corpora: A Morpho-Compositional Approach
Estelle Delpech, Béatrice
Daille, Emmanuel Morin & Claire Lemaire
Challenges in Predicting Machine Translation
Utility for Human Post-Editors
Michael Denkowski & Alon
Lavie
The
Impact of Sentence Alignment Errors on Phrase-Based Machine Translation
Performance
Cyril Goutte, Marine Carpuat
& George Foster
Pivot
Lightly-Supervised Training for Statistical Machine Translation
Matthias Huck & Hermann
Ney
Interpolated
Backoff for Factored Translation Models
Philipp Koehn & Barry Haddow
Building
MT for a Severely Under-Resourced Language: White Hmong
William Lewis & Phong
Yang
Phrase-level System Combination for Machine Translation Based on Target-to-Target Decoding
Wei-Yun Ma & Kathleen
McKeown
Kristen Parton, Nizar Habash & Kathleen McKeown
A
Graph-based Strategy to Streamline Translation Quality Assessments
Daniele Pighin, Lluís Formiga & Lluís Màrquez
Machine
Translation with Binary Feedback: a Large-Margin Approach
Avneesh Saluja, Ian Lane & Ying Zhang
HAL: Challenging Three Key Aspects of IBM-style
Statistical Machine Translation
Christer Samuelsson
Compact Rule Extraction for Hierarchical
Phrase-based Translation
Baskaran Sankaran, Gholamreza Haffari & Anoop Sarkar
Non-linear
n-best List Reranking with Few Features
Artem Sokolov, Guillaume Wisniewski & François Yvon
Improved
Domain Adaptation for Statistical Machine Translation
Wei Wang, Klaus Macherey, Wolfgang Macherey, Franz Och & Peng Xu
Poster
Presentations
Detailed Analysis of Different Strategies for
Phrase Table Adaptation in SMT
Jan
Niehues & Alex Waibel
Machine
Translation of Labeled Discourse Connectives
Thomas Meyer, Andrei Popescu-Belis, Najeh Hajlaoui
& Andrea Gesmundo
A General
Framework to Weight Heterogeneous Parallel Data for Model Adaptation in
Statistical MT
Kashif Shah, Loïc Barrault & Holger
Schwenk
Measuring
User Productivity in Machine Translation Enhanced Computer Assisted Translation
Marcello Federico, Alessandro Cattelan &
Marco Trombetti
Hybrid Machine Translation Using Joint, Binarised Feature Vectors
Christian Federmann
Using
Automatic Machine Translation Metrics to Analyze the Impact of Source
Reformulations
Johann Roturier, Linda Mitchell, Robert
Grabowski & Melanie Siegel
Using
Source-Language Transformations to Address Register Mismatches in SMT
Manny Rayner, Pierrette Bouillon & Barry
Haddow
A
Poor Man's Translation Memory Using Machine Translation Evaluation Metrics
Michel Simard & Atsushi Fujita
A
Detailed Analysis of Phrase-based and Syntax-based MT: The Search for
Systematic Differences
Rasoul Samad Zadeh Kaljahi, Raphael Rubino,
Johann Roturier & Jennifer Foster
Conditional
Significance Pruning: Discarding More of Huge Phrase Tables
J Howard Johnson
Unsupervised
Translation Disambiguation for Cross-Domain Statistical Machine Translation
Mei Yang & Katrin Kirchhoff
Commercial MT User Program
Integrating
MT with Digital Collections for Multilingual Information Access
Jiangping Chen, Olajumoke
Agozu, Wenqian Zhao, Cheng Chieh Lien, Ryan Knudson & Ying Zhang
Linguists
Love Art and Management Loves Efficiency – Can MT be the Solution?
Sachiyo Demizu & Mike
Holland
Taking
Statistical Machine Translation to the Student Translator
Stephen
Doherty,
Dorothy Kenny &
A
User-Based Usability Assessment of Raw Machine Translated Technical
Instructions
Stephen Doherty & Sharon
O’Brien
What’s Your Pick: RbMT, SMT or Hybrid?
Catherine Dove, Olga Loskutova
& Ruben de la Fuente
Evaluation of Domain Adaptation Techniques for
TRANSLI in a Real-World Environment
Atefeh Farzindar
& Wael Khreich
Rustin Gibbs & Joe DiDamo
Translating
User-Generated Content in the Social Networking Space
Jie Jiang, Andy Way &
Rejwanul Haque
Managing Change when Implementing MT Systems
Michel Lopez
Beyond MT: Source Content Quality and Process
Automation
Jenny Lu & Patricia
Paladini Adell
Incremental Re-Training of a Hybrid English-French
MT System with Customer Translation Memory Data
Evgeny Matusov
Multiplying the Potential of Crowdsourcing
with Machine Translation
Victor Muntés-Mulero, Patricia
Paladini, Marc Solé & Jawad Manzoor
Machine Translation as a Global Enterprise
Service at Ford
Craig
Plesco
& Nestor Rychtyckyi
Using
the Microsoft Translator Hub at The Church of Jesus Christ of Latter-day Saints
Stephen D. Richardson
Automatic
Speech Recognition & Hybrid MT for HQ Closed-Captioning & Subtitling
for Video Broadcast
Hassan Sawaf
Spoken
Language Translation: Three Business Opportunities
Mark
Seligman
& Mike Dillinger
IPTranslator: Facilitating Patent Search with
Machine Translation
John
Tinsley,
Alexandru Ceausu, Jian Zhang, Heidi Depraetere & Joeri Van de Walle
Organizer: Jennifer
DeCamp
Government MT User Program
U.S. Army Machine Foreign Language
Translation System (MFLTS) Capability Update and Review
Michael J.
Beaulieu,
Panel Discussion Topic: Return on
Investment for Human Language Technology in the U.S. Government
Nicholas Bemish and Charles Simmons, AMTA 2012 Government Program
Co-Chairs
Language and Translation Challenges in Social Media
Sean Colbath, Raytheon BBN Technologies
Producing Data for Under-Resourced Languages: A Dari-English Parallel
Corpus of Multi-Genre Text
Sherri Condon, MITRE
Machine Translation Revisited: An Operational Reality Check
Kathleen Egan, Technical Support Working Group (TSWG)
Sharpening the Claws on CAT Tools:
Increase Quality & Production, Maximize Limited Resources
Jennifer Flather, Basis Technology
Strategies in Developing
Engine-specific Chinese-English User Parallel Corpora
Weimin Jiang, National Air and
Government Catalog of Language Resources (GCLR)
Judith Klavans, ODNI FLPO, Human Language Technology Lead
A New Method for Automatic Translation Scoring-HyTER
Daniel Marcu, Language Weaver SDL
Return on Investment for Government Human Language Technology Systems
Elaine Marsh, ODNI FLPO Human Language Technology Associate
Evaluating Parallel Corpora: Assessing Utility in Government Translation
Memory (TM) Systems
Erica Michael, Center for Advanced Study of Languages (CASL)
The Conundrum of New Online Languages:
Translating Arabic Chat
Joel Ross, Basis Technology
Reversing the Palladius Mapping of
Chinese Names in Russian Text
Katherine Young, Air Force Research Laboratory (AFRL)
Tutorials
Introduction
to Machine Translation
Mike Dillinger, Principal of Translation
Optimization Partners
Jay Marciano, Director of
Real-Time Translation Development at Lionbridge Technologies
Increasing Localization Efficiency
with SYSTRAN Hybrid MT Products
John Paul Barraza, Director of Technical Services at Systran
Nizar Habash, Research
Scientist at the Center for Computational Learning Systems at
Jost Zetzsche, Independent
Translation and Localization Professional
Open Source Statistical Machine
Translation
Philipp Koehn, Professor for Machine Translation at the
Hieu Hoang, Research Assistant in the Machine Translation group at the
Practical Domain Adaptation in SMT
Marcello Federico, Co-Director, Human Language Technology Research Unit,
Fondazione Bruno Kessler (FBK-irst)
Nicola Bertoldi, Researcher at the Human Language Technology Research
Unit at FBK-irst
Workshop Programs
Workshop on Post-Editing Technology and Practice
(WPTP 2012)
Workshop Organizers:
Sharon O’Brien, Center for Next Generation
Localization, DCU
Michel Simard, National Research Council Canada
Lucia Specia, University of Sheffield
CAASL4: Fourth Workshop on Computational
Approaches to Arabic-Script-based Languages
Workshop
and Program Chairs:
Ali Farghaly, Text Group, Oracle USA, Redwood
Shores, CA
Farhard Oroumchian, University of Wollongong,
Dubai, United Arab Emirates
Workshop on
Monolingual Machine Translation (MONOMT 2012)
Workshop
Chairs:
Tsuyoshi Okita, Dublin City University (DUC),
Artem Sokolov, Laboratoire d’informatique pour la Mécanique et les Sciences
(LIMSI),
Taro Watanabe, National Institute of
Information and Communications Technology (NICT), Japan