Keras implementation (tensorflow backend) of natural language inference

Reading comprehension QA model trained on Squad dataset

Mining Discourse Markers for Unsupervised Sentence Representation Learning

Implementation of the InferSent paper by Conneau et al., EMNLP2017

This project is about developing a document retrieval system to return titles of scientific papers containing the answer to a given user question. Two different sentence embedding approaches have been implemented and compared.

⚕️🦠 Developed a document retrieval system to return titles of scientific papers containing the answer to a given user question based on the first version of the COVID-19 Open Research Dataset (CORD-19) ☣️🧬

Review Opinion Diversification - Shared task in IJCNLP 2017, Taipei, Taiwan

Implementation of a machine learning model to predict COVID-19 Informative Text.

Contextual Thesaurus with Facebook Infersent Embeddings

Vectorization Techniques in Natural Language Processing Tutorial for Deep Learning Researchers

Evaluation of Natural language Inference datasets on State of the art models and their combinations and ensembles.

A project to explore the use of transfer learning in GANs to produce photo realistic images of human faces from its description

Implementation of Facebook's InferSent in Keras as well as a slightly improved version.

Experimented with and compared DFW neural network optimizer with SGD and ADAM on both vision and language tasks

Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference