DeepPavlov
An open source library for deep learning end-to-end dialog systems and chatbots.
APACHE-2.0 License
Bot releases are hidden (Show)
Published by yoptar over 5 years ago
- Full spectrum of BERT-based models
- Multilingual BERT based NER for 100 languages and 19 classes
- Pre-trained BERT-base model for Russian Language
- Updated rusentiment model trained on twitter
- New AIML wrapper component
- New SMN, DAM, DAM-USE-T ranking models
- Minor fixes
Published by seliverstov over 5 years ago
- Multilingual and English BERT-based models for classification and SQuAD
- Knowledge base based Question Answering model
- Refactor train script to class to simplify its modification and extension
- Super-convergence Keras model class
- +3 F1 for speller correction with new custom
vocab_penaltyproperty forsearcher_component - Refactored similarity matching skill
- Add universal method
destroyinComponentclass -
--no-default-skilloptional flag if your component implements an interface of DeepPavlov skill -
--statefuland--multiinstanceflags for Amazon Alexa integration - Move
utilsmodule from project root intodeeppavlovmodule - Many minor improvements and bug fixes, including logging, ELMo save/load and many other
Published by seliverstov over 5 years ago
- ODQA with scores: LogitRanker now returns a batch of best answers and their scores
- Experimental similarity matching skill with updated tutorial
- Amazon EC2 deployment guide
- Links to
RuSentimentdataset were removed due to legal issues - Minor bug fixes
Published by seliverstov almost 6 years ago
- Fix go_bot compatibility with the previous release
- Extended support for env variables in configs
Published by seliverstov almost 6 years ago
- Out-of-the-box Amazon Alexa integration for any skill/model
- New popularity ranking for ODQA
- New fine-tuned models for paraphrase identification
- Support for learning rate & momentum schedulers
Published by seliverstov almost 6 years ago
- Bug fixes and minor improvements
- New ELMO configs
- Manage some settings with
envvariables
Published by seliverstov almost 6 years ago
- Variables in configs and improved python API
- Trainable ELMo model with TF Hub wrapper and support for large datasets
- "Few shot" NER model
- New ODQA model with support for "no answer" response
- Model for sentiment analysis in Russian with ELMo embeddings
- Pretrained model for classification Informational vs. Conversational questions on Yahoo dataset
- eCommerce bot with tfidf retrieve
- Improved logging, including dialog logging for Agents, docs and many other improvements and bug fixes
- Also check out our docker images for popular models on hub.docker.com
Published by seliverstov almost 6 years ago
- Human readable logs
Published by seliverstov almost 6 years ago
- Dialog logging
- API refactoring
- Settings files refactoring
- Other minor improvements and bug fixes
Published by seliverstov almost 6 years ago
- Improved MorphoTagger now supports 10 languages
- Yandex.Alice integration for agents with many skills
- New SQUAD model that supports "no answer" token
- Universal wrapper for
sklearnestimators and vectorizers - New universal interface for metrics calculation
- Many other improvements and bug fixes
Published by seliverstov about 6 years ago
- Integration with Microsoft Bot Framework
- Integration with Yandex.Alice voice assistant
- Support Windows platform
- Upgrade to TensorFlow 1.10
- New features for parameters cross-validation
- New eCommerce Bot
- New Siamese networks for paraphrase identification and ranking
- Many other small improvements and bug fixes
Published by seliverstov about 6 years ago
- FAQ Skill for Russian & English with a tutorial
- Improved Seq2Seq GO Bot: attention over knowledge base, encoder attention, embeddings instead of one-hots
- Pretrainded model for Seq2Seq GO Bot on driver dataset with BLEU=13.2
- Improved ODQA model with squad logits: f1 raised from 14 to 26
- Hashing tf-idf vectorizer component
- Text classifiers now compatible with ELMO embedder
- Improved documentation
- Bug fixes and minor improvements
Published by seliverstov about 6 years ago
- Fix bugs in Morphological Tagging component
- Other minor improvements
Published by yoptar about 6 years ago
- New documentation
- A new ELMO component
- Improved Morphological Tagging component
- CuDNN compatible layers for inference of NER and SQUAD components on CPU
- Bug fixes and minor improvements
Published by yoptar over 6 years ago
- New
show_examplesoption for train and evaluate modes - Bug fixes and minor improvements
Published by seliverstov over 6 years ago
- Split requirements
- Add tutorials
- Support Tensorboard
- Add hyper-parameters evolution
- Some moves, renames and fixes
Published by yoptar over 6 years ago
- Tutorials
- Do not import not used packages
- Per-config requirements
- Bug fixes and minor improvements
Published by yoptar over 6 years ago
- Bug fixes and minor improvements
Published by seliverstov over 6 years ago
- Bug fixes and minor improvements
Published by seliverstov over 6 years ago
- New and blazingly fast spellchecker
- State-of-the-art morphological tagger
- New models for sentiment analysis
- Update to TensorFlow 1.8
- Installation via
pip install deeppavlov - Many bug fixes and minor improvements
