Andy Way's Home Page


Publications

Teaching

Research

Past Postgraduate Students

School Staff Phonebook

Webmail

DCU MT Group

MT Archive

EAMT 2011


Andy Way, B.A., M.Sc., Ph.D.


Associate Professor in Computing
Address: School of Computing, Dublin City University, Glasnevin, Dublin 9, IRELAND.

Tel: +353-1-7005644, Fax: +353-1-7005442, Email: away@computing.dcu.ie

The view from my office window, with thanks!


I am an Associate Professor in the School of Computing at Dublin City University, and have been here since 1991. I am also the School Research Convenor.

I am the Editor for the journal Machine Translation. Please contact me if you would like to submit to the journal.

I am also on the EAMT Committee, from the EAMT-09 conference as the new President of EAMT. DCU also act as Webmaster for EAMT.

Following the MT Summit 2009, I am now the Vice-President for the International Association for Machine Translation, from 2009--2011.

I am also a member of the National Centre for Language Technology (NCLT), and am a member of the Language and Intelligence Research group in our School.

I am also the track leader for Integrated Language Technologies in the Centre for Next Generation Localisation, aiming at facilitating optimal multilingual applications for deployment in the localisation industry.


Recent News

Starting this summer, I am taking three years' leave of absence from DCU to join global translation company Applied Language Solutions full-time to enable the business to further improve its industry-leading services in computer-assisted translation.

DCU have advertised my position as a five-year Professorial appointment, with a deadline of May 6th for potential applicants. DCU wishes to recruit a Research Project Leader with an established international track record and reputation in the area of Machine Translation to join the CNGL's Research Leadership team and lead our large Machine Translation research group.

We've had nine papers accepted for EAMT 2011, which will take place in Leuven, Belgium on 30-31 May, 2011. The papers are as follows:

  • Combining Semantic and Syntactic Generalization in Example-Based Machine Translation : Sarah Ebling, Andy Way, Martin Volk and Sudip Kumar Naskar
  • CCG Contextual labels in Hierarchical Phrase-Based SMT: Hala Almaghout, Jie Jiang and Andy Way
  • Towards Using Web-Crawled Data for Domain Adaptation in Statistical Machine Translation: Pavel Pecina, Antonio Toral, Andy Way, Prokopis Prokopidis and Vassilis Papavassiliou
  • Using Example-Based MT to Support Statistical MT when Translating Homogeneous Data in a Resource-Poor Setting: Sandipan Dandapat, Sara Morrissey, Andy Way and Mikel L. Forcada
  • Oracle-based Training for Phrase-based Statistical Machine Translation: Ankit Srivastava, Yanjun Ma and Andy Way
  • Assessing Three Transcription Methods for Sign Language Machine Translation and Evaluation: Sara Morrissey
  • Experiments on Domain Adaptation for Patent Machine Translation in the PLuTO project: Alexandru Ceausu, John Tinsley, Andrew Way, Jian Zhang and Paraic Sheridan
  • Towards a User-Friendly Webservice Architecture for Statistical Machine Translation in the PANACEA project: Antonio Toral, Marc Poch, Pavel Pecina and Andy Way
  • A Comparative Evaluation of Research vs. Online MT Systems: Antonio Toral, Federico Gaspari, Sudip Kumar Naskar and Andy Way

We've had a paper accepted for ACL-HLT 2011, to take place in Portland on June 19-24, 2011. The paper is entitled Consistent Translation using Discriminative Learning: A Translation Memory-inspired Approach, and represents joint work with Yanjun Ma, Yifan He and Josef van Genabith.

I've just joined global translation company Applied Language Solutions (ALS) in a consultancy role to enable the business to further improve its industry-leading service, through driven development of its machine-assisted translation solution. I will help ALS to continue to develop market-leading machine translation solutions in line with demands from international customers to revolutionize its translation services. See the ALS news item for more details.

The First Call for Papers has just been announced for EAMT-2011: the 15th Annual Conference of the European Association for Machine Translation, to be held in Leuven, Belgium, May 30-31 2011. We hope to see as many of you there as possible!

We've had a paper accepted for IWSLT 2010, to take place in Paris on December 2-3. The paper is entitled CCG-Augmented Hierarchical Phrase-Based Machine Translation, and represents joint work with Hala Al-Maghout and Jie Jiang.

We've had two papers accepted for the International Conference on Asian Language Processing 2010, to take place in Harbin, China, from Dec 28-30, 2010. The papers are entitled:

  • Sentence Similarity-Based Source Context Modelling in PBSMT: Rejwanul Haque, Marta Costa-jussà, Sudip Kumar Naskar, Rafael Banchs and Andy Way
  • Hierarchical Pitman-Yor Language Model in Machine Translation: Tsuyoshi Okita and Andy Way

We've had a paper accepted for EMNLP 2010: Conference on Empirical Methods in Natural Language Processing, to take place from October 9-11, 2010 at MIT, Cambridge MA. The paper is entitled Facilitating Translation Using Source Language Paraphrase Lattices, and represents joint work with Jinhua Du and Jie Jiang.

We've had 2 papers accepted for SSST 2010. The papers are entitled:

  • HMM Word-to-Phrase Alignment with Dependency Constraints: Yanjun Ma and Andy Way
  • Source-side Syntactic Reordering Patterns with Functional Words for Improved Phrase-based SMT: Jie Jiang, Jinhua Du and Andy Way
SSST takes place on 28th August 2010, in Beijing, China, as part of COLING 2010. SSST is endorsed by the ACL SIG in MT.

We've just had a paper accepted for MWE-2010, to be held in Beijing, China on 28th August, 2010, co-located with COLING-2010. The paper is entitled Handling Named Entities and Compound Verbs in Phrase-Based Statistical Machine Translation, and represents joint work with Santanu Pal, Sudip Kumar Naskar, Pavel Pecina, and Sivaji Bandyopadhyay.

We've had 6 papers accepted for AMTA 2010. The papers are entitled:

  • Supertags as Source Language Context in Hierarchical Phrase-Based SMT: Rejwanul Haque, Sudip Kumar Naskar, Antal van den Bosch and Andy Way
  • Using TERp to Augment System Combination for SMT: Jinhua Du and Andy Way
  • Improved Phrase-based SMT with Syntactic Reordering Patterns Learned from Lattice Scoring: Jie Jiang, Jinhua Du and Andy Way
  • Combining Multi-Domain Statistical Machine Translation Models using Automatic Classification: Pratyush Banerjee, Jinhua Du, Sudip Naskar, Baoli Li, Andy Way and Josef Van Genabith
  • Improving the Post-Editing Experience Using Translation Recommendation: A User Study: Yifan He, Yanjun Ma, Johann Roturier, Andy Way and Josef van Genabith
  • Accuracy-Based Scoring for Phrase-Based Statistical Machine Translation: Sergio Penkale, Yanjun Ma, Daniel Galron and Andy Way
In addition, two other papers from the group have been accepted, namely:
  • Maximising TM Performance through Sub-Tree Alignment and SMT: Ventsislav Zhechev
  • f-align: An Open-Source Alignment Tool for LFG f-Structures: Anton Bryl and Josef van Genabith
AMTA takes place in Denver, Colorado, from October 31-November 5, 2010.

We have a number of R&D vacancies to be filled with immediate effect given the award of the EU-funded FP7 project PLUTO (Patent Language Translation Online). These comprise one Post-doctoral research position and two Java Software Development positions. The successful candidates will report to me in the CNGL at DCU. All positions are offered on a fixed-term contract basis to work in the area of MT focused on cross-language search and translation of patent and other Intellectual Property material.

We've had two more papers accepted, namely:

We invite you all to test out our 'Twanslate' application which translates World Cup 2010 tweets from Twitter using our MaTrEx MT system for a range of European languages! This received some nice press in the Sunday Times, and in the Irish Times innovation supplement.

We've had two papers accepted for COLING 2010, which will be held in Beijing from Aug 23-27, 2010. The papers are entitled:

  • A Discriminative Latent Variable-Based DE Classifier for Chinese--English SMT: Jinhua Du and Andy Way
  • SMT-TM Integration as Ranking: Yifan He, Yanjun Ma, Andy Way and Josef Van Genabith

We've had a paper accepted for presentation at Icetal 2010, the 7th International Conference on Natural Language Processing, to take place on August 16-18, 2010, in Reykjavik, Iceland. The paper is entitled OpenMaTrEx: A free/open-source marker-driven example-based machine translation system and is joint work with Sandipan Dandapat, Mikel Forcada, Declan Groves, Sergio Penkale and John Tinsley.

I've just agreed to act as co-Chair (with Patrick Pantel) for Tutorials at the 49th Annual Meeting of the Association for Computational Linguistics, to be held in Portland, Oregon, from June 19-24, 2011.

We've just had a paper published in the Localisation Focus journal. The paper is entitled Integrated Language Technology as part of Next Generation Localisation, and represents work done with Julie Carson-Berndsen, Harold Somers, and Carl Vogel.

We've had three papers accepted for the Joint Fifth Workshop on Statistical Machine Translation and Metrics MATR, to be held at ACL 2010, which will be held in Uppsala, Sweden, on July 15-16, 2010. The three papers are as follows:

  • MaTrEx: The DCU MT System for WMT 2010: Sergio Penkale, Rejwanul Haque, Sandipan Dandapat, Pratyush Banerjee, Ankit K. Srivastava, Jinhua Du, Pavel Pecina, Sudip Kumar Naskar, Mikel L. Forcada and Andy Way
  • The DCU Dependency-based Metric in WMT-Metrics MATR 2010: Yifan He, Jinhua Du, Andy Way and Josef van Genabith
  • An Augmented Three-Pass System Combination Framework: DCU Combination System for WMT 2010: Jinhua Du, Pavel Pecina and Andy Way

We've had a paper accepted for ACL 2010, which will be held in Uppsala, Sweden from 11-16 July, 2010. The paper is entitled Bridging SMT and TM with Translation Recommendation, and is joint work with Yifan He, Yanjun Ma and Josef Van Genabith.

I'm on the programme committee for AMTA-2010, which will be held in Denver, Colorado, from October 31-November 5, 2010.

I'm on the programme committee for the Student Session at the European Summer School in Logic, Language and Information, which will be held at the University of Copenhagen, Denmark, from August 9-20, 2010.

We've had four papers accepted for EAMT 2010, which will be held in St. Raphael, France from 27-28 May, 2010. The papers are as follows:

  • Statistical Analysis of Alignment Characteristics for Phrase-based Machine Translation: Patrik Lambert, Simon Petitrenaud, Yanjun Ma and Andy Way
  • Lattice Score-Based Data Cleaning For Phrase-Based Statistical Machine Translation: Jie Jiang, Andy Way and Julie Berndsen
  • TMX Markup: A Challenge When Adapting SMT to the Localisation Environment: Jinhua Du, Johann Roturier and Andy Way
  • The Impact of Source-Side Reordering on Hierarchical Phrase-Based SMT: Jinhua Du and Andy Way

On 23rd March I gave a presentation of the PLuTO project at the Commission's Language Technology Days event in Luxembourg.

I'm on the programme committee for PACLIC-24, which will be held in Tohoku University, Sendai, Japan, from November 5-7, 2010.

I'm on the programme committee for EAMT 2010, which will be held in St. Raphael, France from 27-28 May, 2010.

Two new journal publications:

  • Metric and Reference Factors in Minimum Error Rate Training: Yifan He and Andy Way, Machine Translation
  • An Incremental Three-pass System Combination Framework by Combining Multiple Hypothesis Alignment Methods: Jinhua Du and Andy Way, International Journal of Asian Language Processing

I'm on the programme committee for ACL 2010, which will be held in Uppsala, Sweden from 11-16 July, 2010.

I'm on the programme committee for COLING 2010, which will be held in Beijing from Aug 23-27, 2010.

I was invited to the third Google Faculty Summit, to take place in Zurich 8-10 February 2010. The Natural Language Technologies stream of the 2010 Europe, Middle East and Africa (EMEA) Faculty Summit will address topics at the intersection of research in Natural Language Understanding and applied techniques for scalable Natural Language Processing.

I'm on the programme committee for NAACL-HLT 2010, which will be held in Los Angeles from June 1-June 6th, 2010

Older Items

News from 2009, Old News from 2008, Older News from 2007, Even Older News from 2006, Really Old News from 2005 & 2004, and Ancient News from 2003 (hardly 'news' at all now!)!



Andy Way, 14th April, 2011.