COVID-19: Comparative Analysis of Methods for Identifying Articles Related to Therapeutics and Vaccines without Using Labeled Data

no code implementations • 5 Jan 2021 • Mihir Parmar, Ashwin Karthik Ambalavanan, Hong Guan, Rishab Banerjee, Jitesh Pabla, Murthy Devarakonda

Here we proposed an approach to analyze text classification methods based on the presence or absence of task-specific terms (and their synonyms) in the text.

text-classification Text Classification +1

Cascade Neural Ensemble for Identifying Scientifically Sound Articles

no code implementations • 13 Apr 2020 • Ashwin Karthik Ambalavanan, Murthy Devarakonda

Conclusion: Pre-trained contextual encoder neural networks (e. g. SciBERT) perform better than the models studied previously and manually created search filters in filtering for scientifically sound relevant articles.

Using Contextual Representations for Suicide Risk Assessment from Internet Forums

no code implementations • WS 2019 • Ashwin Karthik Ambalavanan, Pranjali Dileep Jagtap, Soumya Adhya, Murthy Devarakonda

Our system achieved the 2nd best performance of 0. 477 macro averaged F measure on Task A of the challenge.