Dr. Muhammad Humayoun [On Leave]

Dr. Muhammad Humayoun [On Leave]

Assistant Professor

Faculty of Information technology.

  • Artificial Intelligence
  • Introduction to Machine Learning
  • Discrete Structures
  • Programming Fundamentals
  • Computing for Management
  • Machine Learning (Graduate level)
  • Natural Language Processing  (Graduate level)

Education

Ph.D. in Computer Science (Natural Language Understanding and Technology)
University of Grenoble, France.
Thesis Title: Developing the System MathNat for Automatic Formalization of Mathematical Texts
Master of Computer Science and Engineering
Chalmers University of Technology, Sweden.
Thesis Title: Urdu Morphology, Orthography and Lexicon Extraction

Experience

 Assistant Professor
University of Central Punjab (UCP), Lahore, Pakistan.
Post-doctoral Research Fellow
Toulouse Institute of Computer Science Research (IRIT)
University of Paul Sabatier, Toulouse, France
Assistant Professor
University of Central Punjab (UCP), Lahore, Pakistan.
Assistant Professor
Department of Computer Science
COMSATS Institute of Information Technology (CIIT), Lahore, Pakistan.
Post-doctoral Research Fellow
Data Mining Lab, Department of Computer Science and Engineering
POSTECH, Pohang, Korea
Software development Engineer (internship)
XEROX Research Center Europe: Grenoble, France.

R&D Projects:

STAC Project
Toulouse Institute of Computer Science Research (IRIT), University of Paul Sabatier, Toulouse, France
STAC is an ERC funded project that aims to develop a new formal and robust model of conversation. As a post-doctoral research fellow, I work with renowned professor (Dr. Nicholas Asher) and other STAC members. I am working in two complementary directions, (1) Integrating rich lexical information using distributional representations in the prediction of discourse structure, and, (2) exploiting features of the extra-linguistic context.
 Single Document Text Summarization System for Urdu
COMSATS Institute of Information Technology, Pakistan and University of Central Punjab, Pakistan
A software tool for Single Document Summarization (SDS) for Urdu was developed using unsupervised machine learning algorithms. In addition, a benchmark corpus was developed to facilitate various experiments for SDS for Urdu. For instance, the effect of different stopword lists and the effect of various stemming and lemmatization was analyzed as benchmarking experiments.
Technologies: Java, PHP
 Prototype: The System MathNat for Automatic Formalization of Math Texts
University de Savoie, France
A prototype the system MathNat (Mathematics in controlled Natural language) was developed as proof of concept during my PhD. The system allows writing mathematical proofs found in textbooks using a controlled language. This controlled language was developed in Grammatical Framework. It is further translated in a formal description language called MathAbs, which is later translated into first order language. This transfer module was developed in Haskell.
Technologies: Shell scripting, Haskell, Grammatical Framework
 Linguistic resources for Urdu and Punjab
Developed at various places including Chalmers University of Technology, Sweden and University de Savoie, France
A suite of computational resources for Urdu and Punjabi was developed from time to time including a fairly complete morphology, lexicon and small fragment of syntax. The corpora was built from online texts (such as ripping Wikipedia, news websites, blogs, etc.), and the lexicons were extracted semi-automatically. These resources were transformed into ready-to-use open source software.
Technologies: Shell scripting, Java, Haskell
Software development Engineer (internship)
XEROX Research Center Europe: Grenoble, France.
Developed Extraction Transformation and Load Service to back up a fault prediction algorithm deployed at XEROX. Developed some graphic widgets for visualization of the data
Technologies: Shell scripting, Java, C#

Peer-reviewed Publications

Conferences:

  • Muhammad Humayoun, Rao Muhammad Adeel Nawab, Muhammad Uzair, Saba Aslam and Omer Farzand (2016). Urdu summary corpus. In Nicoletta Calzolari, et al., editors, Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016). European Language Resources Association (ELRA). ISBN: 978-2-9517408-9-1.
  • Muhammad Humayoun and Hwanjo Yu (2016), Analyzing Pre-processing Settings for Urdu Single-document Extractive Summarization. In Nicoletta Calzolari, et al., editors, Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016). European Language Resources Association (ELRA). ISBN: 978-2-9517408-9-1.
  • Muhammad Salman Khan, Adnan Ahmad, Muhammad Humayoun (2014). A Survey of Current Opportunities for Developing Automated Assessment System for C/C++ Programing Assignments. Proceedings of 28th Annual Conference of the Asian Association of Open Universities. The Hong Kong University, Hong Kong, China.
  • Jinoh Oh, Youngchul Sung, Jinha Kim, Muhammad Humayoun, Young-Ho Park, Hwanjo Yu (2012). Time-Dependent User Profiling for TV Recommendation. Second International Conference on Cloud and Green Computing (CGC 2012), 10.1109/CGC.2012.119, Page(s): 783 – 787. IEEE Conference Publications
  • Shafqat M. Virk, M. Humayoun, A. Ranta (2011). An Open Source Punjabi Resource Grammar. Proceedings of the 8th International Conference on Recent Advances in Natural Language Processing (RANLP 2011). (Ranking: 0.54, in range 0.00–1.00, short paper acceptance rate: 38%)
  • Humayoun and C. Raffalli (2010). MathAbs: A Representational Language for Mathematics. 8th International Conference on Frontiers of Information Technology. December 21-23, 2010, Islamabad, Pakistan. ACM 978-1-4503-0342-2/10/12. (Acceptance rate: 29.25%)
  • Humayoun and A. Ranta (2010). Developing Punjabi Morphology, Corpus and Lexicon. In R. Otoguro, K. Ishikawa, H. Umemoto, K. Yoshimoto, and Y. Harada, editors, Proceedings of the 24th Pacific Asia Conference on Language, Information and Computation (PACLIC24). Pages 163–172. Tohoku University, Japan, November 2010. ISBN 978–4–905166–00–9. (Acceptance rate:27.45%)
  • Shafqat M. Virk, M. Humayoun, A. Ranta (2010). An Open Source Urdu Resource Grammar. Proceedings of the Eight Workshop on Asian Language Resources. August 2010, Beijing, China. Co-located with Coling 2010. (Acceptance rate: 62.86%)
  • Humayoun, H. Hammarstrom, and A. Ranta (2007). Urdu Morphology, Orthography and Lexicon Extraction. In Ali Farghaly & Karine Megerdoomian (eds.), Proceedings of the 2nd Workshop on Computational Approaches to Arabic Script-based Languages. Pages 59–68, LSA 2007 Linguistic Institute, Stanford University, USA. (Acceptance rate: not mentioned, but frequently cited paper)

Journals:

  • Humayoun and C. Raffalli (2010). MathNat – Mathematical Text in a Controlled Natural Language. Special issue: Natural Language Processing and its Applications. Journal on Research in Computing Science. Volume 46. ISSN:1870-4069. CICLing 2010:11th International Conference on Intelligent Text Processing and Computational Linguistics, March 21-27, 2010, Iasi, Romania. (Acceptance rate: 27%).


+92-42-35880007 Ext: 133
Faculty of Information Technology, University of Central Punjab

Apply Online