deepPavlov
| Original author(s) | Mikhail Burtsev |
|---|---|
| Developer(s) | DeepPavlovTeam,various |
| Initial release | February 2018[1] |
| Stable release | 0.7.0[2]
|
| Written in | Python 3.6 and Python 3.7 |
| Engine | |
| Operating system | Linux, Windows |
| Platform | cross-platform |
| Type | Natural language processing |
| License | Apache 2.0 |
| Website | deeppavlov.ai |
Search DeepPavlov on Amazon.
DeepPavlov (DP) is an open-source conversational AI library for advanced natural language processing (NLP)[3], written in the programming languages Python[4]. DeepPavlov is designed for the development of production-ready chat-bots and complex conversational systems and research in the area of NLP and, particularly, of dialog systems[5]. The main goal is to provide an easy way to deploy the latest developments in the sphere of human-machine conversation to production and contribute to the technological development of conversational AI.
DeepPavlov library also supports deep learning workflows that allow connecting statistical models trained by popular machine learning libraries like TensorFlow and Keras and is published under the license Apache 2.0[6]. It contains a set of components for quick dialog system prototyping. The library currently offers statistical neural network models for Russian, English, German and multi-language. Solutions developed on DeepPavlov help automate communication processes in marketing, sales, and customer support, enable product and information search in a dialog assistant’s interface, and automate a contact center’s work.
DeepPavlov was developed by the Neural Networks and Deep Learning Lab at the Moscow Institute of Physics and Technology (MIPT).
DeepPavlov library resume[edit]
DeepPavlov library was released in February 2018 and got more than 4 100 stars and 100,000 downloads as of now.
Key concepts[edit]
- Agent is a conversational agent communicating with users in natural language (text). DeepPavlov Agent helps production chatbot developers to organize multiple NLP models in a single pipeline.[7]
DeepPavlov components[edit]
- Context Question Answering[8]
- Classification[9]
- Morphological Tagger
- Named entity recognition[10]
- Slot filling
- Spelling Correction[11]
- TF-IDF Ranking
- Popularity Ranking
- Knowledge Base Question answering
- FAQ
Community[edit]
We also organize international educational initiatives and events, such as machine learning courses, schools, competitions, and hackathons. See details at DeepHack. Check out the latest recordings on our YouTube channel.
References[edit]
- ↑ "DeepPavlov 0.0.1 (pre-alpha)". Retrieved 2018-02-05.
- ↑ "DeepPavlov 0.7.0".
- ↑ "DeepPavlov: Open-Source Library for Dialogue Systems" (PDF). Proceedings of ACL 2018, System Demonstrations.
- ↑ "Introducing DeepPavlov". DeepPavlov.ai.
- ↑ "How to build 'Hello World!' bot with DeepPavlov in 4 steps".
- ↑ "DeepPavlov: An open-source library for end-to-end dialogue systems and chatbots".
- ↑ "DeepPavlov.Agent".
- ↑ "Simple intent recognition and question answering with DeepPavlov".
- ↑ "Simple text classification skill of DeepPavlov".
- ↑ "19 entities for 104 languages: A new era of NER with the DeepPavlov multilingual BERT".
- ↑ "Build AIML chatbot with DeepPavlov Spelling Corrector".
External links[edit]
 | This scientific software article is a stub. You can help EverybodyWiki by expanding it. |
This article "DeepPavlov" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:DeepPavlov. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
