31 Open Source Dialogue Generation Software Projects

RNNLG is an open source benchmark toolkit for Natural Language Generation (NLG) in spoken dialogue system application domains. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.

NNDial is an open source toolkit for building end-to-end trainable task-oriented dialogue models. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.

This repository contains a new generative model of chatbot based on seq2seq modeling.

A list of recent papers regarding dialogue generation

GoNorth is a story and content planning tool for RPGs and other open world games.

Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow

Code for "MojiTalk: Generating Emotional Responses at Scale" https://arxiv.org/abs/1711.04090

The implementation of the paper "Augmenting Neural Response Generation with Context-Aware Topical Attention"

Generating responses with pretrained XLNet and GPT-2 in PyTorch.

Dynamic Knowledge-Grounded Dialogue Generation

Repository to generate CLEVR-Dialog: A diagnostic dataset for Visual Dialog

Source code for the paper "Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering".

A pytorch implementation for the MMI-anti model

A Paper List for Open-Domain Dialogue Generation, and related datasets.

A PyTorch Implementation of japanese chatbot using BERT and Transformer's decoder

MoEL: Mixture of Empathetic Listeners

code for CIKM'18 long paper, Explicit state tracking with semi-supervision for neural dialogue generation

Record papers for some NLP related area

Source code for our EMNLP19 paper "Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework"

Dialogue Knowledge Transfer Networks (DiKTNet)

Code for EMNLP 2019 paper "Modeling Multi-Action Policy for Task-Oriented Dialogues"

Code for "Polite Dialogue Generation Without Parallel Data"

CVAE_XGate model in paper "Xu, Dusek, Konstas, Rieser. Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity"

The codebase for "Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation" (Cai et al., AAAI 2020)

This repository contains the dataset and the PyTorch implementations of the models from the paper Recognizing Emotion Cause in Conversations.

Code for ACL 2021 main conference paper "Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances".

Code for "Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation". [AAAI 2021]

The PyTorch implementation of ReCoSa(the Relevant Contexts with Self-attention) for dialogue generation using the multi-head attention and GRU.

Training chatbot models with reinforcement learning in ParlAI.