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 IgnatovFedor about 3 years ago
- A distilled Russian BERT
- New Pytorch-based models for classification, question answering and named entity recognition
- Removed some configuration files and components
- Small fixes and updates
Published by IgnatovFedor over 3 years ago
- bert_as_summarizer, seq2seq_go_bot, hyperparameter optimization by neural evolution and all deeppavlov.deprecated components were removed
- NER automodel
- Сomponent-based config requirements generation
- Minor edits and fixes
Published by IgnatovFedor over 3 years ago
- Fixed installation on python3.6
Published by IgnatovFedor almost 4 years ago
- Intent Catcher component
- Support of the Hugginface Transformers for classification
- Go-Bot formfilling (tutorial)
- Entity Linking, Wiki Parser and KBQA as separate components
- Minor edits and fixes
Published by IgnatovFedor almost 4 years ago
- Hugging Face datasets support
- Go-Bot now requires only RASA-based configs to train its components (intent catcher, slot filler, dialogue state tracker also known as Go-Bot itself)
- Prometheus metrics middleware for REST web service
- KBQA models fixes
- Minor edits of the documentation
Published by IgnatovFedor about 4 years ago
- Entity Linking for Wikidata (English)
- Bugfixes in KBQA model
- Other minor improvements
Published by IgnatovFedor about 4 years ago
- PyTorch Support (w/ Examples)
- Multi-task BERT
- Basic RASA Configs Support for Go-Bot
- Entity Linking
-
top_nAnswers API Update in ODQA Models - Hybrid NER Models Trained on OntoNotes: Ru | En
- BoolQ Dataset Reader
Published by IgnatovFedor over 4 years ago
- Dataset generation tool with a tutorial for Goal-Oriented Dialog Bot
- Undocumented feature for downloading artifacts from Amazon s3
- New KBQA pipeline for online version of Wikidata
- First version of a KBQA pipeline using Syntax tree for generating SPARQL-queries
- And many small improvements and fixes
Published by yoptar over 4 years ago
- New Knowledge Base Question Answering model for WikiData
- Training interfaces for KBQA models
- Refactored goal-oriented bot architecture
- And many small improvements and fixes
Published by yoptar over 4 years ago
- Fix requirements for ASR and TTS configs
Published by yoptar over 4 years ago
- A dataset reader for the IMDB Large Movie Review Dataset and sample configurations for training classifiers on it
- Models for speech recognition and synthesis based on NVIDIA NeMo
- A New hybrid NER model pre-trained for English and Vietnamese languages
- A pre-trained NER-based Model for Sentence Boundary Detection Task
- Many smaller changes and fixes
Published by yoptar over 4 years ago
- Configuration and model for DRCD (Chinese SQUAD) based on Chinese BERT
- Remove all Keras usage in favor of
tensorflow.keras - Start refactoring of goal-oriented bot code
- Update dependencies versions
- Add a BERT-embedding component as a first step of moving from google-research/bert to HuggingFace's Transformers
- Release BERT-based sentence embedders models
- Smaller changes and fixes
Published by yoptar almost 5 years ago
Published by yoptar almost 5 years ago
- Replace Flask with FastAPI everywhere
- A syntax parser model
- Deprecate Agent and Skill classes in favor of DeepPavlov Agent
- Change DeepPavlov settings structure
- Code style fixes
- Many smaller changes and fixes
Published by yoptar about 5 years ago
- New gobot tutorial
- Replace Flask with FastAPI for riseapi
- New section in quickstart documentation about out-of-the-box pretrained models
- Minor NER dataset reader fix
- Other minor documentation changes
Published by yoptar about 5 years ago
- New risesocket mode
- A wrapper for Rasa skills
- New gobot tutorial
- Conversational Bert in Russian
- Minor fixes and documentation updates
Published by yoptar about 5 years ago
- Downloads resuming after interruptions
- Small documentation tweaks
- Multilingual SQUAD configuration for inference
Published by yoptar about 5 years ago
- Conversational BERT model in English (trained on informal lexicon data)
- Updated requirements
- Python 3.7 support
- New DSL for building rule-based skills
- New SOTA insult-detection model based on the conversational BERT
- Updated documentation
- Refactored MorphoTagger classes to better conform DeepPavlov ideology
- Many smaller changes and fixes
Published by yoptar over 5 years ago
- New rule-based obscenity classifier for Russian language
- Lemmatization option in Morphotagger pipeline for Russian language
- Unification of default configuration variables as per #844
- Fixes in knowledge base dataset readers
- other minor fixes
Published by yoptar over 5 years ago
- Fixes in documentation
- Compressed BERT-based models
- Minor fixes
