Deeppavlov

- Entity Linking for Wikidata (English)
- Bugfixes in KBQA model
- Other minor improvements

- [PyTorch Support](http://docs.deeppavlov.ai/en/master/intro/choose_framework.html#text-classification-on-keras-or-pytorch) (w/ Examples)
- [Multi-task BERT](http://docs.deeppavlov.ai/en/master/features/models/multitask_bert.html)
- Basic [RASA Configs Support](http://docs.deeppavlov.ai/en/master/features/skills/go_bot.html#quick-start-rasa-dsls) for Go-Bot
- [Entity Linking](http://docs.deeppavlov.ai/en/master/features/models/entity_linking.html)
- `top_n` Answers API Update in ODQA Models
- Hybrid NER Models Trained on OntoNotes: [Ru](https://github.com/deepmipt/DeepPavlov/blob/dev/deeppavlov/configs/ner/ner_collection3_m1.json) | [En](https://github.com/deepmipt/DeepPavlov/blob/dev/deeppavlov/configs/ner/ner_ontonotes_m1.json)
- [BoolQ](https://github.com/google-research-datasets/boolean-questions) Dataset [Reader](https://github.com/deepmipt/DeepPavlov/blob/dev/deeppavlov/dataset_readers/boolqa_reader.py)

- Dataset generation tool with a [tutorial](https://github.com/deepmipt/DeepPavlov/blob/0.11.0/deeppavlov/contrib/examples/Dataset_generation_tutorial.ipynb) for Goal-Oriented Dialog Bot
- Undocumented [feature](https://github.com/deepmipt/DeepPavlov/pull/1246) for downloading artifacts from Amazon s3
- [New KBQA pipeline](https://github.com/deepmipt/DeepPavlov/blob/0.11.0/deeppavlov/configs/kbqa/kbqa_cq_online.json) for online version of Wikidata
- First version of a [KBQA pipeline](https://github.com/deepmipt/DeepPavlov/blob/0.11.0/deeppavlov/configs/kbqa/kbqa_cq_rus.json) using Syntax tree for generating SPARQL-queries
- And many small improvements and fixes

- [New Knowledge Base Question Answering](http://docs.deeppavlov.ai/en/0.10.0/features/models/kbqa.html) model for WikiData
- [Training interfaces](http://docs.deeppavlov.ai/en/0.10.0/features/models/kbqa.html#train-models) for KBQA models
- Refactored [goal-oriented bot](http://docs.deeppavlov.ai/en/0.10.0/features/skills/go_bot.html) architecture
- And many small improvements and fixes

- Fix requirements for ASR and TTS configs

- A dataset reader for the [IMDB Large Movie Review Dataset](https://ai.stanford.edu/~amaas/data/sentiment/) and [sample configurations](https://github.com/deepmipt/DeepPavlov/blob/0.9.0/deeppavlov/configs/classifiers/sentiment_imdb_conv_bert.json) for training classifiers on it
- [Models for speech recognition and synthesis](http://docs.deeppavlov.ai/en/0.9.0/features/models/nemo.html) based on [NVIDIA NeMo](https://github.com/NVIDIA/NeMo)
- A New hybrid NER model pre-trained for [English](https://github.com/deepmipt/DeepPavlov/blob/0.9.0/deeppavlov/configs/ner/conll2003_m1.json) and [Vietnamese](https://github.com/deepmipt/DeepPavlov/blob/0.9.0/deeppavlov/configs/ner/vlsp2016_full.json) languages
- A pre-trained [NER-based Model for Sentence Boundary Detection Task](http://docs.deeppavlov.ai/en/0.9.0/features/models/ner.html#ner-based-model-for-sentence-boundary-detection-task)
- Many smaller changes and fixes