DeepPavlov: An Open Source Library for Conversational AI

Mikhail Burtsev, Alexander Seliverstov, Rafael Airapetyan, Mikhail Arkhipov, Dilyara Baymurzina, Eugene Botvinovsky, Nickolay Bushkov, Olga Gureenkova, Andrey Kamenev, Vasily Konovalov, Yuri Kuratov, Denis Kuznetsov, Alexey Litinsky, Alexey Lymar, Maxim Petrov, Leonid Pugachev, Alexey Sorokin, Maria Vikhreva

Keywords: dialogue systems, natural language processing, chat bot

TL;DR: DeepPavlov is an open source library and framework for dialogue systems research, fast prototyping and deployment.

Abstract: An open-source DeepPavlov library is specifically tailored for development of dialogue systems. The library prioritizes efficiency, modularity, and extensibility with the goal to make it easier to create dialogue systems from scratch with limited data available. It supports modular as well as end-to-end approaches to implementation of conversational agents. In DeepPavlov framework an agent consists of skills and every skill can be decomposed into components. Components are usually trainable models which solve typical NLP tasks such as intent classification, named entity recognition, sentiment analysis or pre-trained encoders for word or sentence level embeddings. Sequence-to-sequence chit-chat, question answering or task-oriented skills can be assembled from components provided in the library. ML models implemented in DeepPavlov have performance on par with current state of the art in the field.

Decision: accept