Windows Build of fastText, library for text representation and classification.

Public release of data and code for materials synthesis generation

A set of tools for leveraging pre-trained embeddings, active learning and model explainability for effecient document classification

A PyTorch implementation of Global Vectors (GloVe).

Analysis and Visualizations for COVID-19 Bing search engine queries + Classifier pipeline for predicting country based on search query.

Mini blog for notes and guides on Natural Language Processing (Open Notes)

Engineered an advanced deep learning model to automate the classification of financial documents, including Balance Sheets, Cash Flow and Income Statements using Bidirectional LSTM and TensorFlow. The model achieved an impressive accuracy of 96.2%, enhancing efficiency and reducing errors in document management for the finance and banking sectors.

Neural Network machine translation using a Sequence-to-Sequence model

Real time application of Sentiment Analysis on Movie Reviews. A Machine Learning Flask App hosted on Heroku and created on Google Colab. https://swetakesurnlp-playground.herokuapp.com

MatNexus is an end-to-end software for the automated collection and analysis of scientific articles' text, streamlining literature retrieval and offering powerful visualization and machine learning capabilities for material science research.Scientific literature processing for Materials Science

Spring 2023 graduation thesis for mathematical engineering program of Istanbul Technical University

Setup https://github.com/hanxiao/bert-as-service in a minute.

Intent classification is the automatic categorization of text data based on customer goals. It is known to be a complex problem in NLP. Sequence Labelling aims to classify each token (word) in a class space C. This project addresses these two problem statements by covering the basic concepts of NLP to advanced ones. For instance, linguistics ana…

In this project, my colleague Catherine Lee (Rutgers) and I employ computational text analysis to examine quantitative trends in the use of diversity terms, OMB/Census terms, and other population labels in a sample of 2.6+ million biomedical abstracts spanning the last 30 years.

Tag semantic-driven search engine for DLsite. Demo: https://dlfilter.moe

Generate a TV script using RNNs

A simple web app that uses a trained sequential neural net to predict the rating of a hotel review.

Snippets of the additional code used in personal blog