Our goal is to enable AI-application developers and researchers with:
A set of pre-trained NLP models, pre-defined dialog system components (ML/DL/Rule-based), and pipeline templates;
A framework for implementing and testing their own dialog models;
Tools for application integration with adjacent infrastructure (messengers, helpdesk software, etc.);
Benchmarking environments for conversational models and uniform access to relevant datasets.
Skillfulfills the user’s goal in some domain. Typically, this is accomplished by presenting information or completing transaction (e.g. answer question by FAQ, booking tickets, etc.). However, for some tasks, a successful interaction is defined as continuous engagement (e.g. chit-chat).
Modelis any NLP model that doesn’t necessarily communicates with the user in natural language.
Componentis a reusable functional part of a
Rule-based Modelscannot be trained.
Machine Learning Modelscan be trained only stand alone.
Deep Learning Modelscan be trained independently and in an end-to-end mode being joined in a chain.
Skill Managerperforms selection of the
Skillto generate the response.
Chainerbuilds a model pipeline from heterogeneous components (Rule-based/ML/DL). It allows one to train and infer models in a pipeline as a whole.
The smallest building block of the library is a
Component stands for any kind of function in an NLP pipeline. It can
be implemented as a neural network, a non-neural ML model, or a
Components can be joined into a
Model or a
solves a larger NLP task than a
Component. However, in terms of
Models are not different from
What differentiates a
Skill from a
Model is that
the input and output of a
Skill should both be strings.
Skills are usually associated with
DeepPavlov is built on top of the machine learning frameworks TensorFlow, Keras and PyTorch. Other external libraries can be used to build basic components.