DRIFT is a tool for Diachronic Analysis of Scientific Literature. The application offers user-friendly and customizable utilities for two modes: Training and Analysis. Currently, the application supports customizable training of diachronic word embeddings with the TWEC model. The application supports a variety of analysis methods to monitor trends and patterns of development in the scientific literature.

This site is an experiment: a living literature review that allows you to explore, search and navigate the literature in the research area of Semantic Parsing, by following a taxonomy based on the underlying design principles of each model.

DecepticoNLP is a Python Library for Robustness Monitoring and Adversarial Debugging of NLP models

(we are looking for active contributors!)