|
Welcome to the website of the Machine Translation (MT) group in the School of Computing at DCU.
The research that we carry out is undertaken in the National Centre for Language Technology (NCLT),
and the Centre for Next Generation Localisation (CNGL). We carry out a wide range of research in MT, including: |
- Syntax-Driven Statistical Machine Translation [Projects: Prospect]
- Hybrid Statistical & Example-Based Machine Translation
- Tree-Based Machine Translation [Projects: Attempt]
- Sub-sentential Alignment for Machine Translation [Projects: Attempt]
- Probabilistic Transfer-Based Machine Translation
- Evaluation in Machine Translation [Project: Syntax-Based MT Evaluation]
- Controlled Language & Machine Translation
- Human Factors in Machine Translation [Project: Data-Driven Sign Language MT]
|
I'm delighted to announce some of our new recruits, including:
- Prof. Mikel L. Forcada
- Dr. Marianna Apidianaki
- Dr. Anton Bryl
- Mr. Sandipan Dandapat
- Dr. Jinhua Du
- Mr. Rejwanul Haque
- Mr. Yifan He
- Dr. Patrik Lambert
- Dr. Sudip Naskar
- Mr. Tsuyoshi Okita
- Mr. Sergio Penkale
- Prof. Harold Somers
- Mr. Ankit Srivastava
See our People section for futher information
|
| Once all the new CNGL staff and students are in place, our MT team here will constitute 25 people. The CNGL is bringing in 5 postdoctoral researchers, and 9 PhD students, as well as a well-known Professor! |
| Harold, as well as supervising one postdoctoral and 2 PhD researchers, will be joining us after Coling 2008 as Education and Outreach Director in the CNGL. I'm pleased to announce that Sara Morrissey, who's just finished her PhD thesis with me, will be staying with us as Harold's postdoc. |
We'll continue to get involved in large-scale MT evaluation campaigns, and remain determined to make some of our software available in the public domain in the near future.
While the group is almost fully complemented now, there will probably be more advertised positions soon, so keep an eye on this page for more announcements, as we're involved in some potential FP7 projects as well as collaborative research with industry.
We have formed links with some of the leading groups in the fields of MT , where we carry out joint research, host research visits and submit joint research proposals. We would be delighted to become actively involved with more research groups, so contact us if interested. |
| Thanks for accessing our site, and let us know if it did or did not meet your expectations -- if there's something wrong, or missing, we can only fix it if you let us know! |
| -- Andy Way, April 2008 |
|
| Recent News |
 Nov 17 - We've just had two journal papers accepted for publication. The first paper is entitled Metric and Reference Factors in Minimum Error Rate Training and will appear in Machine Translation (with Yifan and Andy). The second paper is entitled An Incremental Three-pass System Combination Framework by Combining Multiple Hypothesis Alignment Methods and will appear in the International Journal of Asian Language Processing (with Jinhua and Andy) |
| Nov 17 - Andy has been 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. |
| Nov 17 - Andy is on the programme committee for NAACL-HLT 2010, which will be held in Los Angeles from June 1-June 6th, 2010. He is also on the programme committee for COLING 2010, which will be held in Beijing from Aug 23-27, 2010, and for ACL 2010, which will be held in Uppsala, Sweden from 11-16 July, 2010. |
| Oct 28 - We've just had three papers accepted for presentation at the 3rd Workshop on Example-Based Machine Translation, which will be held on November 12–-13 2009 at Dublin City University. The papers are entitled Hybrid Rule-Based -- Example-Based MT: Feeding Apertium with Sub-sentential Translation Units (with Felipe Sánchez-Martínez, Mikel, and Andy), Evaluating Syntax-Driven Approaches to Phrase Extraction for MT (with Ankit, Sergio, Declan and John), and A review of EBMT using proportional analogies (with Harold, Sandipan and Sudip) |
| Sep 30 - We've just had three papers accepted for presentation at the 23rd Pacific Asia Conference on Language, Information and Computation (PACLIC 23), which will be held on September 3--5 2009 at the City University of Hong Kong. The papers are entitled Experiments on Domain Adaptation for English--Hindi SMT (with Rejwanul, Sudip, Josef and Andy), Capturing lexical variation in MT evaluation using automatically built sense-cluster inventories (with Marianna, Yifan and Andy), and Dependency Relations as Source Context in Phrase-Based SMT (with Rejwanul, Sudip, Antal van den Bosch and Andy) |
| Sep 23 - Following the IAMT business meeting at MT Summit XII in Ottawa, Canada, a new IAMT Committee has been confirmed for the 2009-2011 period, including Andy as President-Elect |
|