Sudip Kumar Naskar's Home Page


Profile

Publications

Webmail

Important links
Sudip Kumar Naskar

Postdoctoral Researcher
Address: L2.01, School of Computing, Dublin City University, Glasnevin, Dublin 9, IRELAND.

Tel: +353-1-700 6714, Fax: +353-1-700 6702, Email: snaskar@computing.dcu.ie, sudip.naskar@gmail.com

I am a post-doctoral researcher, working on Integrated Language Technology, in the Centre for Next Generation Localisation, at MT Research Group, National Centre for Language Technology, School of Computing, Dublin City University. I am also working part time in the EU-FP7 project CoSyne. I work with Prof. Andy Way and some great MT people.

Recent News

  • We've just had a paper accepted for JEC 2011, which will be held on 14th October, 2011, in Luxembourg. The paper is:
    • User-Focused Task-Oriented MT Evaluation for Wikis: A Case Study: Federico Gaspari, Antonio Toral, Sudip Kumar Naskar and Andy Way.

  • We've just had two papers accepted for MT Summit XIII, which will be held 19-23 September, 2011 in Xiamen, China. The papers are:
    • Domain Adaptation in Statistical Machine Translation of User-Forum Data using Component Level Mixture Modelling: Pratyush Banerjee, Sudip Kumar Naskar, Johann Roturier, Andy Way and Josef Van Genabith.
    • A Framework for Diagnostic Evaluation of MT based on Linguistic Checkpoints: Sudip Kumar Naskar, Antonio Toral, Federico Gaspari and Andy Way.

  • We've just had a paper accepted for the journal Machine Translation. The paper is:
    • Integrating Source-Language Context into Phrase-Based Statistical Machine Translation: Rejwanul Haque, Sudip Kumar Naskar, Antal van den Bosch and Andy Way.

  • We've just had two papers accepted for EAMT-2011, which will be held 30-31 May, 2011 in Leuven, Belgium. The papers are:
    • Combining Semantic and Syntactic Generalization in Example-Based Machine Translation: Sarah Ebling, AndyWay, Martin Volk and Sudip Kumar Naskar.
    • A Comparative Evaluation of Research vs. Online MT Systems: Antonio Toral, Federico Gaspari, Sudip Kumar Naskar and Andy Way.

  • CNGL Scientific Committee Meeting is being held November 11th-12th at The Hub, DCU.
  • Attended CNGL Localisation Innovation Showcase hosted at Microsoft European Development Centre (EDC), Dublin.

  • Attended AMTA-2010, Denver.

  • From October 1st, I am also in the CoSyne project and will work 50% of my time in it.

  • We've just had a paper accepted in ICON 2010, which will be held during 8-11 December, 2010 at IIT Kharagpur, India. The paper is:
    • Statistically Motivated Example-based Machine Translation using Translation Memory.: Sandipan Dandapat, Sara Morrissey, Sudip Kumar Naskar and Harold Somers.

  • We've just had a paper accepted in IALP 2010, which will be held December 28—30, 2010 in Harbin, China. The paper is:
    • Sentence Similarity-Based Source Context Modelling in PBSMT.: Rejwanul Haque, Marta R. Costa-jussà , Sudip Kumar Naskar, Rafael E. Banchs and Andy Way.

  • Attended COLING 2010, Beijing, China.

  • We've just had a paper accepted for PACLIC 24, which will be held November 4th-7th, 2010 in Sendai, Japan. The paper is:
    • Mitigating Problems in Analogy-based EBMT with SMT and vice versa: a Case Study with Named Entity Transliteration: Sandipan Dandapat, Harold Somers, Sara Morriessy and Sudip Kumar Naskar.

  • We've just had two papers accepted for AMTA 2010, which will be held October 31—November 5, 2010 in Denver, Colorado. The papers are:
    • Supertags as Source Language Context in Hierarchical Phrase-Based SMT: Rejwanul Haque, Sudip Kumar Naskar, Antal van den Bosch and Andy Way.
    • Combining Multi-Domain Statistical Machine Translation Models using Automatic Classification: Pratyush Banerjee, Jinhua Du, Sudip Kumar Naskar, Baoli Li, Andy Way and Josef Van Genabith.

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

  • In WMT-2010 English-to-Czech shared task on system combination, the DCU MT Group has secured the top spot among 17 systems, yet another feather to DCU's cap, thanks to Jinhua's magic wand.

  • We've had a paper accepted for WMT-2010, which will be held in Uppsala, Sweden from 15-16 July, 2010, co-located with ACL-2010. The paper is:
    • 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, Andy Way.

  • CNGL Spring Scientific Committee Meeting is being held from April 27th to 29th at the Localisation Research Centre (LRC) on the picturesque campus of University of Limerick. You can find the published version of the CNGL 2009 Annual Report here.

  • We've had a paper accepted for NTCIR-8, which will be held in Tokyo, Japan from 15-18 June, 2010. The paper is:
    • MaTrEx: the DCU MT System for NTCIR-8: Tsuyoshi Okita, Jie Jiang, Rejwanul Haque, Hala Al-Maghout, Jinhua Du, Sudip Kumar Naskar and Andy Way.

  • I coordinated our participation in the WMT-2010 shared task on translation. In En-Es, top 5 of the 6 submissions are from us, another world-beating performance from the DCU MT Group. In En-Cz, we stand 3rd in the constrained track.

  • We participated in the NTCIR-8 Patent Translation Task. In EN-JP direction, we stood second, next to NICT. In extrinsic evaluation, the best 2 system submissions, according to MAP (Mean Average Precision), are from us.

  • The Fourth Machine Translation Marathon, January 25-30, is being organised by the National Centre for Language Technology and the Centre for Next Generation Localisation at Dublin City University on behalf of the EuroMatrixPlus Consortium.

  • I am on the local organising committee for 3rd Workshop on Example-Based Machine Translation to be held at DCU November 12-13, 2009.

  • We've had a paper accepted for 3rd Workshop on Example-Based Machine Translation to be held at DCU November 12-13, 2009. The paper is:
    • A review of EBMT using proportional analogies: Harold Somers, Sandipan Dandapat and Sudip Naskar.

  • CNGL Scientific Meeting is being held here from October 14th to 16th at The Helix, DCU. Two (of the 8) ACL Lifetime Achievement awardees, Frederick Jelinek (2009) and Lauri Karttunen (2007), as well as Dion Wiggins, CEO of AsiaOnline, were present in the meeting.

  • We've had two papers accepted for PACLIC 23, the 23rd Pacific Asia Conference on Language, Information and Computation, to be held 3-5 December at the City University of Hong Kong. The papers are:
    • Experiments on Domain Adaptation for English--Hindi SMT: Rejwanul Haque, Sudip Kumar Naskar, Josef van Genabith and Andy Way
    • Dependency Relations as Source Context in Phrase-Based SMT: Rejwanul Haque, Sudip Kumar Naskar, Antal van den Bosch and Andy Way

  • I'm coordinating the activities of our EBMT research group consisting of Andy Way, Harold Somers, Mikel L. Forcada, David Farwell, Declan Groves, Sandipan Dandapat, Ankit Srivastava, Tsuyoshi Okita and myself.

  • We've had a paper accepted for presentation at the project exhibition at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), which will take place in Bled, Slovenia, from September 7th to 11th, 2009. The paper is entitled Noise Reduction Experiments in Machine Translation, and is joint work with Tsuyoshi Okita and Andy Way.

  • The 3rd Workshop on Example-Based Machine Translation is going to be held here at DCU, November 12-13, 2009.

    • Sudip Kumar Naskar, 6th March, 2010.