Utsab Barman

PhD Student

School Of Computing,
Dublin City University.

Hi, Currently I am a PhD student at School of Computing, Dublin City University (DCU), Dublin, Ireland. I did my Masters in Computer Technology from Jadavpur University, kolkata, India. I was a Senior Research Engineer in CLIA project Jadavpur University.

Research Areas: Natural Language Processing, Machine Learning. My current research area is realated to code-mixing, specially in Indian languages.




  1. Code-Mixing Corpus

    This corpus is a collection of 11K public Facebook comments and posts. Most of them are code-mixed. The most dominant language in this corpus is Bengali followed by English and then Hindi (the national language of India). This corpus is manually annotated at word level with proper language information. It can be used language identification, part-of-speech tagging and named entity tagging.

    To obtain a copy please mail at:

    1. Research Purpose Only: ubarman AT computing DOT dcu DOT ie
    2. Commercial Use: collaboration AT adaptcentre DOT ie