Burcu Can

Assistant Professor
Department of Computer Engineering
Hacettepe University

email: burcucan at cs dot hacettepe dot edu dot tr

I am mainly interested in unsupervised learning techniques applied to natural language processing.


My affiliation has changed to University of Wolverhampton, Research Institute in Information and Language Processing.

Please check my new homepage.

Short biography

I completed my B.Sc. and M.Sc. in the Department of Computer Engineering, Hacettepe University. I completed my Ph.D. in 2011 in the Computer Science Department, University of York as a member of the Artificial Intelligence group and under the supervision of Suresh Manandhar). I was also a visiting researcher for 9 months in 2014 in the Department of Computer Science at the University of York.

I am affiliated at the Department of Computer Engineering, Hacettepe University at the moment.

Research interests

I work on problems related to Natural Language Processing with the application of unsupervised learning techniques. These include statistical methods such as nonparametric Bayesian learning. In particular, I am interested in morphology and syntax.

Lately, I am also interested in deep learning techniques applied to language in order to learn representations of agglutinative languages.

Latest News

Past Projects

Supervision

Current: Former: If you are interested in working with me as a MSc or PhD student and if you think that your interests match mine, please feel free to contact me.

Teaching

2019-2020 Spring:

In the past:

Professional

  • Associate Editor on ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)
  • The Conference on Artificial Intelligence (AAAI) 2020 (Program committee)
  • International Conference on Language Resources and Evaluation (LREC) 2017, 2020 (Program committee)
  • Association for Computational Linguistics (ACL) 2016, 2017, 2018, 2019, 2020 (Program committee)
  • EMNLP-IJCNLP 2019 (program committee)
  • 4th Workshop on Representation Learning 2019 (https://sites.google.com/view/repl4nlp2019/home) (workshop organizer)
  • NAACL 2019 (Program committee)
  • COLING 2016, 2018 (Program committee)
  • IJCNLP 2013, 2017 (Program committee)
  • Journal of Natural Language Engineering (JNLE) - 2015 (Reviewer)
  • Information Processing and Management - 2017, 2018 (Reviewer)
  • International Journal of Data Mining Science (editorial board) 2017
  • IEEE Signal Processing and Communications Applications Conference (SIU) 2017, 2018, 2019 (Program committee)
  • Turkish Journal of Electrical Engineering & Computer Sciences - 2013-2016 (Reviewer), 2018-2019 (editorial board)
  • Linguistics and Literature Studies - Horizon Research Publishing - 2015 (Reviewer)
  • York Doctoral Symposium (YDS) 2009 and 2010 (Program committee)
  • Morpho Challenge Workshop 2008 and 2009 (Program committee)
  • Publications

    Journal Publications

  • Agglutination and Multi-task Learning of Morphology and Syntax.
    Burcu Can, Hüseyin Aleçakır, Suresh Manandhar, Cem Bozşahin.
    The Journal of Natural Language Engineering, Cambridge University Press. (under review)
  • A Cascaded Unsupervised Model for PoS Tagging.
    Necva Bölücü and Burcu Can.
    ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP). (in press)
  • Incorporating Word Embeddings in Unsupervised Morphological Segmentation.
    Ahmet Üstün and Burcu Can.
    The Journal of Natural Language Engineering, Cambridge University Press. 2020 (in press)
  • Transfer Learning for Turkish Named Entity Recognition on Noisy Text
    Emre Kağan Akkaya and Burcu Can.
    The Journal of Natural Language Engineering, Cambridge University Press. 2020
  • Stemming Turkish Words with LSTM Networks
    Burcu Can.
    Bilişim Teknolojileri Dergisi. July 2019, Vol.12, No:3.
  • Unsupervised Joint PoS Tagging and Stemming for Agglutinative Languages
    Necva Bölücü and Burcu Can.
    ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP). February 2019, Vol. 18, No. 3
  • Turkish Lexicon Expansion by Using Finite State Automata
    Burak Öztürk and Burcu Can.
    Turkish Journal of Electrical Engineering and Computer Science. December 2018. Vol. 27:1012-1027
  • Tree Structured Dirichlet Processes for Hierarchical Morphological Segmentation
    Burcu Can and Suresh Manandhar.
    Computational Linguistics. MIT Press Journal. June 2018, Vol. 44, No.2.
    [pdf | code]
  • Unsupervised Learning of Allomorphs in Turkish
    Burcu Can.
    Turkish Journal of Electrical Engineering and Computer Science. 2017.
    [pdf]
  • Conference Publications

  • Using Morpheme-Level Attention Mechanism for Turkish Sequence Labelling
    Yasin Eşref and Burcu Can.
    27. Sinyal İşleme ve İletişim Uygulamaları Kurultayı, Sivas, 2019.
  • Context Based Automatic Spelling Correction for Turkish
    Necva Bölücü and Burcu Can.
    Elektrik-Elektronik Bilgisayar, Biyomedikal Mühendislikleri Bilimsel Toplantısı (EBBT), İstanbul, April 2019. IEEE Xplore.
  • Analysis of Adversarial Attacks against Traditional Spam Filters
    Hüseyin Burhan Özkan, Sevil Şen, Burcu Can
    International Conference on All Aspects of Cyber Security, Adana, 2019.
  • Neural Sentiment Analysis of User Reviews to Predict User Ratings
    Bahar Gezici, Necva Bölücü, Ayça Tarhan, Burcu Can.
    The 4th International Conference on Computer Science and Engineering (UBMK 2019), IEEE CPS.
  • Neural Text Normalization for Turkish Social Media
    Sinan Göker and Burcu Can.
    32. Uluslararası Bilgi​sayar Bilimleri ve Mühendisliği ​Konferansı, UBMK 2018, Saray Bosna, Bosna Hersek. 2018.
  • Characters or Morphemes: How to Represent Words?
    Ahmet Üstün, Murathan Kurfalı, and Burcu Can.
    3rd Workshop on Representation Learning for NLP (RepL4NLP), ACL 2018, Melbourne, Australia. (Best Paper Award)
    [pdf | code, data]
  • The Role of Letter Frequency on Eye Movements in Sentential Pseudoword Reading
    C. Acartürk, Ö. Kılıç, B. Kırkıcı, B. Can, A. Özkan.
    The 39th Annual Meeting of the Cognitive Science Society, 2017.
    [pdf]
  • A Trie-Sructured Bayesian Model for Unsupervised Morphological Segmentation.
    Murathan Kurfalı, Ahmet Üstün, Burcu Can.
    18th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2017), Budapest, Hungary 2017.
  • Joint PoS Tagging and Stemming for Agglutinative Languages.
    Necva Bölücü, Burcu Can.
    18th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2017), Budapest, Hungary 2017.
  • Stem-based PoS Tagging for Agglutinative Languages.
    Necva Bölücü, Burcu Can.
    25. IEEE Sinyal İşleme ve İletişim Uygulamaları Kurultayı (SIU 2017), Antalya, Mayıs 2017.
    [pdf]
  • Buildings Morphological Chains for Agglutinating Languages.
    Serkan Özen, Burcu Can.
    18th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2017), Budapest, Hungary 2017.
  • Modelling Morpheme Triplets with a Three-level Hierarchical Dirichlet Process.
    Serkan Kumyol, Burcu Can.
    20th International Conference on Asian Language Processing (IALP 2016), Tainan, Taiwan, 2016.
    [pdf]
  • Unsupervised Morphological Segmentation Using Neural Word Embeddings.
    Ahmet Üstün, Burcu Can.
    4th International Conference on Statistical Language and Speech Processing (SLSP 2016), Pilsen, Czech Republic, 2016.
    [pdf]
  • Turkish PoS Tagging by Reducing Sparsity with Morpheme Tags in Small Datasets.
    Burcu Can, Ahmet Üstün, Murathan Kurfalı.
    17th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2016), Konya, Turkey, 2016.
    [pdf]
  • Clustering Word Roots Syntactically.
    M. Burak Öztürk, Burcu Can.
    24. IEEE Sinyal İşleme ve İletişim Uygulamaları Kurultayı (SIU 2016), Zonguldak, Mayıs 2016.
    [pdf]
  • Allomorphs and Binary Transitions Reduce Sparsity in Turkish Semi-supervised Morphological Processing.
    Burcu Can, Serkan Kumyol, Cem Bozşahin.
    The First Conference on Turkic Computational Linguistics (TurCLing), Konya, Turkey, 2016.
    [pdf]
  • Methods and Algorithms for Unsupervised Learning of Morphology.
    Burcu Can, Suresh Manandhar.
    Computational Linguistics and Intelligent Text Processing, Lecture Notes in Computer Science, Springer, 2014.
    [pdf]
  • A Syllable-Based Turkish Speech Recognition System by Using Time Delay Neural Networks.
    Burcu Can, Harun Artuner.
    5th International Conference of Soft Computing and Pattern Recognition (SoCPaR 2013). Hanoi, Vietnam. 2013.
  • Dirichlet Processes for Joint Learning of Morphology and PoS Tags.
    Burcu Can, Suresh Manandhar.
    6th International Joint Conference on Natural Language Processing 2013 (IJCNLP 2013). Nagoya, Japan. 2013.
    [pdf]
  • An Agglomerative Hierarchical Clustering Algorithm for Morpheme Labelling.
    Burcu Can, Suresh Manandhar.
    Recent Advances in Natural Language Processing 2013 (RANLP 2013). Hissar, Bulgaria. September, 2013.
    [pdf]
  • Probabilistic Hierarchical Clustering of Morphological Paradigms.
    Burcu Can, Suresh Manandhar.
    EACL 2012. Avignon, France. April 2012.
    [pdf]
  • Clustering Morphological Paradigms Using Syntactic Categories.
    Burcu Can, Suresh Manandhar.
    Revised Selected Papers Notes in Computer Science. Springer, 2010.
    [pdf]
  • Unsupervised Learning of Morphology by Using Syntactic Categories.
    Burcu Can, Suresh Manandhar.
    CLEF 2009, Corfu, Greece.
    [pdf]
  • Personal

    My hobbies include:

    Contact Information

    Hacettepe Üniversitesi
    Bilgisayar Mühendisliği Bölümü
    06800 Beytepe Ankara
    Türkiye
    03122977500
    email: burcucan at cs dot hacettepe dot edu dot tr


    Last modified: Mon May 23 17:31:26 BST 2016