🦄 State-of-the-Art Conversational AI with Transfer Learning

Code for "Interpreting Word Embeddings with Eigenvector Analysis" https://openreview.net/forum?id=rJfJiR5ooX.

Personalizing Dialogue Agents via Meta-Learning

Code to run baseline experiments and evaluation scripts for the two sub-tasks in SemEval 2020 Task 7.

Source code for transferable dialogue state generator (TRADE, Wu et al., 2019). https://arxiv.org/abs/1905.08743

Hierarchical Attention for Dialogue Emotion Classification (SemEval, NAACL)

simple text preprocessing tool

A natural language modeling framework based on PyTorch

Neural Abstractive Text Summarization with Sequence-to-Sequence Models

Some example code that shows you how to use Sacred in a full Pytorch project.

High-coverage and high-precision lexica of terms annotated with emotion scores for English and Italian.

Implementation of Universal Transformer in Pytorch

😇A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc

Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems

Well tested & Multi-language evaluation framework for text summarization.

State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc.

A statistical modelling toolkit, providing all the tools required to build, fit, visualize, and test deformable models.