An open source library for deep learning end-to-end dialog systems and chatbots.

CakeChat: Emotional Generative Dialog System

User Simulation for Task-Completion Dialogues

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.

NIPS Conversational Intelligence Challenge 2017 Winner System: Skill-based Conversational Agent with Supervised Dialog Manager

ConvAI baseline solution

A collection of document for ChatScript dialog engine

An empathetic counselling chatbot. Retrieval-based, uses finetuned LMs for emotion identification and to boost empathy, novelty and fluency of the retrieved responses. Backend: Python, frontend: Javascript.

Code tor the SIGDIAL 2019 paper Flexibly-Structured Model for Task-Oriented Dialogues. It implements a deep learning end-to-end differentiable dialogue system model

MakeCents is a dialogue system designed to help coin collectors quickly query coin prices.

User Simulation for Task-Completion Dialogues

Dialog policy optimization for task-oriented conversational agents in low resource setting using Reinforcement learning. The methodology is based on a novel probability based Self-play technique and a novel Reward based sampling technique that prioritizes failed dialogues over successful ones

The AVATAR project demonstrates virtual characters that play the role of a police officer or a witness in a police interview.

A comprehensive survey for recent advances and trends in dialogue system

Goal-oriented open-ended counselling chatbot. Modular goals are added according to dialogue history and executed by priority via conditional prompts passed to an LLM. Uses Vicuna 13B as base model.

Conversation alignment for debugging dialogue-as-planning agents.

Semantic Textual Similarity and Dialogue System package for Python

A dialogue bot for information access

User Simulation for Task-Completion Dialogues