Shashwath Krishna's repositories
Hierarchical-Seq2Seq
A PyTorch implementation of the hierarchical encoder-decoder architecture (HRED) introduced in Sordoni et al (2015). It is a hierarchical encoder-decoder architecture for modeling conversation triples in the MovieTriples dataset. This version of the model is built for the MovieTriples dataset.
Relation-Extraction-using-CNN
A Chainer implementation of a Convolutional Network model for relation classification in the SemEval Task 8 dataset. This model performs Multi-Way Classification of Semantic Relations Between Pairs of Nominals in the SemEval 2010 task 8 dataset.
Semisupervised-learning-with-DCGANs
Using DCGANs to learn useful representations during the adversarial training process and using the learned features to classify images with relatively little training data
Extrinsic-Evaluation-tasks
A suite of tasks for extrinsic evaluation of word embedding models.
Sequence-Labeling
A repository for performing NER, POS tagging and Chunking using the CoNLL-2003 dataset using a simple window based concatenation of word embeddings.
Clinical-Concept-Extraction
Clinical Concept Classification using Bidirectional LSTM and word embeddings
Sentence-Classification-with-CNN
A Chainer implementation of a Convolutional Network model for sentence classification in movie reviews dataset.
Recurrent-Language-Model
Pytorch implementation of a simple GRU word-level language model trained on Donald Trump's tweets.
blog
Repo for personal blog
cats-vs-dogs-classifier
A simple Convolutional Neural Network that is a binary classifier of cat and dog images
InOne-File-Manager
A java desktop application that manages your local filesystem
protobuf
Protocol Buffers - Google's data interchange format
spacy-pytorch-transformers
🛸 spaCy pipelines for pre-trained BERT, XLNet and GPT-2