Research Work

This page is underconstruction. Please feel free to reach out to me via email.

I am an NLP researcher with an experience in applying machine learning and deep learning algorithms to problems in computational linguistics. In my research career, I have worked on several NLP problems with solutions involving unsupervised and supervised models , and deep neural network models. A few problem areas I have worked on are mentioned below:

  • Neural machine translation
  • Statistical machine translation
    • Word alignment
    • Unsupervised transliteration of unknown words
    • Domain adaptation
  • Machine translation evaluation
    • Using eye-tracking to improve human evaluation
  • Practical Machine Translation
  • Transliteration mining
    • Unsupervised and semi-supervised models
  • Part-of-speech tagging
    • Urdu part-of-speech tagset and statistical tagging
  • Morphologically rich language prcoessing
    • Arabic and Russian
    • Arabic unsupervised segmentation
  • Resource poor language processing
    • Dialectal Arabic processing and translation
    • Dialectal Arabic spelling normalization
    • Hindi-Urdu machine translation
    • Roman Urdu lexical normalization
  • Social media analysis
    • Supervised learning
    • Domain adaptation
    • Distant supervision
  • Informal text processing
    • Roman Urdu and Arabic dialects
  • Query refinement


  1. Belinkov, Y., Màrquez, L., Sajjad, H., Durrani, N., Dalvi, F., & Glass, J. (2017). Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks. In Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP).
  2. Dalvi, F., Durrani, N., Sajjad, H., Belinkov, Y., & Vogel, S. (2017). Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder. In Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP).
  3. Belinkov, Y., Durrani, N., Dalvi, F., Sajjad, H., & Glass, J. (2017). What do Neural Machine Translation Models Learn about Morphology? In Proceedings of the 55th Conference of the Association for Computational Linguistics (ACL).

© 2017. All rights reserved.

Powered by Hydejack v6.6.1