I'm a final year Computer Science PhD student at Indian Institute of Technology (IIT) Patna, India advised by Dr. Asif Ekbal and co-advised by Dr. Sriparna Saha and Prof. Pushpak Bhattacharyya in the AI-NLP-ML group IIT Patna

My research focuses on the development of deep learning techniques for solving NLP problems: entity & relation extraction, document classification and document similarity from biomedical and clinical text. Currently I'm focused on analyzing and predicting the severity of medical condition by exploiting social-media text - in particular, devising medical sentiment to capture the severity of medical condition.

Recent News

  • May 2019 — Our paper "A Unified Multi-task Adversarial Learning Framework for Pharmacovigilance Mining" has been accpted in ACL 2019.
  • January 2018 — Visited Kno.e.sis, Wright State University, USA as a short term research scholar hosted by Prof Amit Sheth on the project “Harrasment Detection from Social Media”.
  • September 2017 — Attended Google NLP Summit at Google Office, Zurich.
  • April 2017 — Attended EACL and presented our paper .
  • March 2017 — I received Google India Travel Grant for presenting our paper at EACL-2017, Spain. Thank you Google!
  • September 2016 — Visited Kno.e.sis, Wright State University, USA as a short term research scholar hosted by Prof Amit Sheth in the project “Alchemy for HealthCare” and “Harrasment Detection from Social Media”.

Publications

2019

A Unified Multi-task Adversarial Learning Framework for Pharmacovigilance Mining
Shweta Yadav, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya
Association for Computational Linguistics (ACL 2019) (accpted).

2018

Feature Assisted bi-directional LSTM Model for Protein-Protein Interaction Identification from Biomedical Texts
Shweta Yadav, Asif Ekbal, Sriparna Saha, Ankit Kumar, and Pushpak Bhattacharyya
Knowledge-based System (Elsevier) Impact Factor: 4.4

Relation extraction between the clinical entities based on the shortest dependency path based LSTM
Dhanachandra Ningthoujam; Shweta Yadav; Pushpak Bhattacharyya ; Asif Ekbal
15th International Conference on Natural Language Processing (ICON 2018).

Information Theoretic-PSO based Feature Selection: An Application in Biomedical Entity Extraction
Shweta Yadav, Asif Ekbal and Sriparna Saha
Knowledge and Information Systems (KAIS) Journal (Springer), Impact Factor: 2.3

Multi-task Learning Framework for Mining Crowd Intelligence towards Clinical Treatment
Shweta Yadav, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya and Amit Sheth
North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL) 2018.

Medical Sentiment Analysis using Social Media: Towards building a Patient Assisted System
Shweta Yadav, Asif Ekbal, Sriparna Saha and Pushpak Bhattacharyya
Language Resources and Evaluation Conference (LREC) 2018.

2017

Feature Selection for Entity Extraction from Multiple Biomedical Corpora: A PSO based Approach
Shweta, Asif Ekbal, Sriparna Saha
Soft Computing Journal (Springer), Impact Factor: 2.2

Entity Extraction in Biomedical Corpora: An Approach to Evaluate Word Embedding Features with PSO based Feature Selection
Shweta, A Ekbal, S Saha, P Bhattacharyya
European Chapter of the Association for Computational Linguistics (EACL-2017)

Patient Data De-Identification: A Conditional Random-Field-Based Supervised Approach
Shweta, A Ekbal, S Saha, PS Pathak, P Bhattacharyya
Handbook of Research on Applied Cybernetics and Systems Science (Book Chapter), 234-253

2016

A deep learning architecture for protein-protein Interaction Article identification
Shweta, A Ekbal, S Saha, P Bhattacharyya
23rd International Conference on Pattern Recognition (ICPR), 3128-3133

A Recurrent Neural Network Architecture for De-identifying Clinical Records
Shweta, Ankit, A Ekbal, S Saha, P Bhattacharyya
13th International Conference on Natural Language Processing, 188-197

Deep learning architecture for patient data de-identification in clinical records
Shweta, Ankit, A Ekbal, S Saha, P Bhattacharyya
International Workshop ClinicalNLP in Conjunction with COLING-2016, 32-41

A Hybrid Approach for Entity Extraction in Code-Mixed Social Media Data
Deepak Gupta, Shweta, S Tripathi, A Ekbal, P Bhattacharyya
Shared Task on Code Mix Entity Extraction in Indian Languages (CMEE-IL) in conjuction with FIRE-2016

2015

PSO-Asent: Feature selection using particle swarm optimization for aspect based sentiment analysis
Deepak Gupta, Kandula Srikanth Reddy, Shweta , Asif Ekbal
International Conference on Applications of Natural Language to Information Systems 2016, 220-233

Projects

  • Alchemy for Healthcare: This project aims to develop robust model by intelligently augmenting semantics to deep learning technique for biomedical and clinical information extraction task such as entity extraction, relation extraction, event identification and medical severity identification.
  • Context-Aware Harrasment Detection on Social Media: The aim of this project is to develop comprehensive and reliable context-aware techniques (using machine learning, text mining, natural language processing, and social network analysis) to glean information about the people involved and their interconnected network of relationships, and to determine and evaluate potential harassment and harassers.
  • Medical Case-Similarity: The goal of this project is to design sophisticated technique (exploring deep learning, semantics web, machine learning and natural language processing) for determining the cases, similar to a patient who is currently under medical observation in order to improve suggestion based on past records.

CV

You can have a look at my CV here.