Welcome to my homepage!

Hoang Cuong

Visiting Address:

Room F1.22
Building F
Science Park 107
1098 XG Amsterdam
Google Scholar
Email: c.hoang [at] uva [dot] nl                            

Hoang Cuong

Hi! I am a PhD student (since Oct 2013) at the ILLC, University of Amsterdam. My PhD advisers are Khalil Sima'an and Ivan Titov.

The main research topic for my PhD thesis is about Domain Adaptation for Statistical Machine Translation. Domain adaptation methods aim to utilize a small data sample exemplifying the target domain for the learning. We approach the problem with our proposed novel latent domain variable models for adaptation (see [1][2][3]).

Of course, in practice, the target domain may not be known at training time or it may change over time depending on user needs. This raises a very hard problem of Online Adaptation. Recently, we are close to deal with the challenge (see [4]). If you are interested in it, drop me an email!

In general, I am an MT nerd. I enjoy learning/thinking about how to improve translation using Machine Learning/Statistics all my day. That (kind of) stamina is perhaps the strongest ability I have!

News

Selected Publications

2016
  • Adapting to All Domains at Once: Rewarding Domain Invariance in SMT (pdf) (Code)
    Hoang Cuong, Khalil Sima'an and Ivan Titov
    Transactions of the Association for Computational Linguistics (TACL) 2016

  • ILLC-UvA Adaptation System (Scorpio) at WMT'16 IT-Domain Task. (pdf)
    Hoang Cuong, Stella Frank and Khalil Sima'an
    Proceedings of the First Conference on Machine Translation (WMT) 2016 (Shared Task Papers)

2015
  • Latent Domain Word Alignment for Heterogeneous Corpora (pdf) (poster)
    Hoang Cuong and Khalil Sima'an
    North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT) 2015

2014
  • Latent Domain Translation Models in Mix-of-Domains Haystack (pdf) (slides) (Code for reference) (revised and extended version)
    Hoang Cuong and Khalil Sima'an
    International Conference on Computational Linguistics (COLING) 2014

  • Latent Domain Phrase-based Models for Adaptation (pdf) (slides)
    Hoang Cuong and Khalil Sima'an
    Empirical Methods on Natural Language Processing (EMNLP) 2014


Last updated: Feb 19 2016
Page view: web page hit counters codes Free