Niraj Kumar

Researcher & Educationalist


Additional URL:

Mobile: 91+8585928474; 91+8142710442

View Niraj Kumar's profile on LinkedIn

Academic Qualifications

I obtained my PhD, (CSE) from IIIT-Hyderabad (June-2015), under the guidance of Dr. Kannan Srinathan and Dr. Vasudeva Varma (Prof. and Dean R&D, IIIT-Hyderabad).

PhD Thesis Title: Towards Intelligent Text Mining: Under Limited Linguistic Resources.

Achievements Related to PhD Thesis: My system was in Top system for "Automatic Summarization Evaluation Task" at Text Analysis Conference, organized by National Institute of Standards and Technology (NIST), Gaithersburg, Maryland, USA, TAC-2010 and TAC-2011. (See Result: TAC-2010, TAC-2011 )

Imp: TAC and TREC is considered as top US based evaluation and benchmarking organization for research in the area of NLP/IR.

The thesis can be downloaded from:

Experience (6+ Years)

1. Scientist III (Senior Scientist), Computer Science & Eng. at Conduent Labs (Bangalore, India), (Apr-2018 to Now) Role: (a) Leadership role, (b) bringing new research projects with strong business alignment, (c) mentoring team members, and (d) conducting high-level R&D works.

Research Projects:

  • Niraj Kumar and team; A Deep Learning based Fully Automated Cyber Hate Profiling System (“Awarded by the Company”, Submitted for Patenting process).
  • Niraj Kumar and team; A Deep Learning based Fully Automatic Crime Volume Prediction System (Filed US Patent, Patent ID - 87979419)
  • Niraj Kumar and team; An Automatic Hate Target Identification System (Filed US Patent- Patent ID - 87979416).
  • Anant Khandelwal, Niraj Kumar; An Automated System for Aggression Identification in Online Texts (Accepted in CODS-COMAD-2020, ID Submitted).
  • Niraj Kumar and team: Quantification of emotion and sentiment in calls and chats. (Investigation Disclosure Submitted)
  • Anant Khandelwal, Niraj Kumar; Automated Aspect + Target Sentiment Classifier.

2. Senior Machine Learning Scientist, Phenom People (Dec 2016 to Feb-2018) Role: (a) Leadership role, (b) bringing new research projects with strong business alignment, (c) mentoring team members, and (d) conducting high-level R&D works.

Research Projects:

  • Developed a novel weighted knowledge graph for (a) Smart B-2-B-2-C hiring, (b) Contextual and (c) Personalized Search.
  • Candidate Social Graph for automatic resource arrangements and supporting business planners and
  • Automatic Job-Highlight System.

3. Post-Doctoral Researcher at University of California (Davis) (Sep-2015 to Sep-2016);

Research Project:

  • “Automatic identification of taxonomy of knowledge from software engineering documents”.

4. Research Professional, TCS Innovation Lab, New Delhi (May 2013 to Aug-2015)

Research Projects:

  • Automatic Plagiarism Detection system (highly effective in the case of paraphrasing and major word re-ordering). (winner of the best paper award 1st place @ CICLing-2014)
  • Automatic text-quality grading system (Effectively grades the quality of E-mails, without relevant background model).
  • Automatic event detection, alignment and prediction system (related to the economic events).

5. Research Intern; IBM IRL; Bangalore, India (May 2012 – July 2012)

Research Projects:

  • Developed a new system to answer - “Why based questions” with the help of Wikipedia dump.

Research Interests

My research interests broadly span five areas and more specifically their intersection: Human Language Technology, Deep Learning, Machine Learning, Social Media Mining and Artificial Intelligence.

Some of the areas, in which I have worked or currently working (including but not limited to):

  • Knowledge Representation: Knowledge Graph Construction, Dynamic Ontology, Dynamic Contextual Search System.
  • NLP Psycholinguistic/Analytic Features: Weighted Sentiment Analysis, Sarcasm Detection, Emotion (Anger, Fear, Joy/happiness, & Sadness, etc.) Extraction, Valence, Arousal Dominance Extraction.
  • NLP (related to Social Media): Hate Speech and Hate Target Classifier, Aggression Identification from Text, Automatic extraction of Threat, Insult, Complain and Cyberbullying.
  • NLP General: Keyphrase Extraction, Named Entity Extraction, Entity Normalization, Single & Multi-document Summarization (Extract, Abstract and Guided Summarization), Summarization Evaluation, Text Clustering, Classification, Automatic Question Answering, Automatic Plagiarism Detection.
  • Recommendation System.
  • Conversational AI: Switching the control from Bot to Human, Intent Classification, Dialogue Selection and so on.
  • Code Mixed NLP Applications