Recurrent Neural Networks (RNN, GRU, LSTM) and their Bidirectional versions (BiRNN, BiGRU, BiLSTM) for word & character level language modelling in Theano

TensorFlow implementation of Z. Hu et al. "Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Prediction", WSDM 2018

Deep Learning model to tackle the Fake News Challenge

Can sarcastic sentences be identified?

Learn to code deep learning algorithms

Deep Learning for Approximate String Matching

This project is about to detecting the text generated by different LLM given prompt. The instance is labeled by Human and Machine, and this project utilised both traditional machine learning method and deep learning method to classify the instance.

Siamese Manhattan Bi-GRU for semantic similarity between sentences

Build Bi-directional GRU to predict the degradation rates at each base of an RNA molecule which can be useful to develop models and design rules for RNA degradation to accelerate mRNA vaccine research and deliver a refrigerator-stable vaccine against SARS-CoV-2, the virus behind COVID-19.

Sentiment analysis (text mining and opinion mining) uses Natural Language Processing to determine whether data is positive, negative or neutral. Sentiment analysis is often performed on textual data to help businesses monitor brand and product sentiment in customer feedback, and understand customer needs.

bi-rnn language model

Sentiment analysis on the IMDb dataset through a custom multivariate Bernoulli Naive Bayes implementation and a rudimentary BiGRU RNN.

"Detect toxic content to improve online conversations"

Developing a Sarcasm Detection Solution using Machine Learning and Deep Learning Approaches

Sentiment analysis using different types of Bidirectional Recurrent Neural Networks on Amazon reviews dataset. The results are confronted with two baseline models which are an SVM and a RF model.