QuickStart

First, follow instructions on Installation page to install deeppavlov package for Python 3.6/3.7.

DeepPavlov contains a bunch of great pre-trained NLP models. Each model is determined by it’s config file. List of models is available on the doc page or in the deeppavlov.configs:

from deeppavlov import configs

When you’re decided on the model (+ config file), there are two ways to train, evaluate and infer it:

Before making choice of an interface, install model’s package requirements (CLI):

python -m deeppavlov install <config_path>
  • where <config_path> is path to the chosen model’s config file (e.g. deeppavlov/configs/ner/slotfill_dstc2.json) or just name without .json extension (e.g. slotfill_dstc2)

Command line interface (CLI)

To get predictions from a model interactively through CLI, run

python -m deeppavlov interact <config_path> [-d]
  • -d downloads required data – pretrained model files and embeddings (optional).

You can train it in the same simple way:

python -m deeppavlov train <config_path> [-d]

Dataset will be downloaded regardless of whether there was -d flag or not.

To train on your own data you need to modify dataset reader path in the train section doc. The data format is specified in the corresponding model doc page.

There are even more actions you can perform with configs:

python -m deeppavlov <action> <config_path> [-d]
  • <action> can be
    • download to download model’s data (same as -d),

    • train to train the model on the data specified in the config file,

    • evaluate to calculate metrics on the same dataset,

    • interact to interact via CLI,

    • riseapi to run a REST API server (see docs),

    • risesocket to run a socket API server (see docs),

    • interactbot to run as a Telegram bot (see docs),

    • interactmsbot to run a Miscrosoft Bot Framework server (see docs),

    • predict to get prediction for samples from stdin or from <file_path> if -f <file_path> is specified.

  • <config_path> specifies path (or name) of model’s config file

  • -d downloads required data

Python

To get predictions from a model interactively through Python, run

from deeppavlov import build_model

model = build_model(<config_path>, download=True)

# get predictions for 'input_text1', 'input_text2'
model(['input_text1', 'input_text2'])
  • where download=True downloads required data from web – pretrained model files and embeddings (optional),

  • <config_path> is path to the chosen model’s config file (e.g. "deeppavlov/configs/ner/ner_ontonotes_bert_mult.json") or deeppavlov.configs attribute (e.g. deeppavlov.configs.ner.ner_ontonotes_bert_mult without quotation marks).

You can train it in the same simple way:

from deeppavlov import train_model

model = train_model(<config_path>, download=True)
  • download=True downloads pretrained model, therefore the pretrained model will be, first, loaded and then train (optional).

Dataset will be downloaded regardless of whether there was -d flag or not.

To train on your own data you need to modify dataset reader path in the train section doc. The data format is specified in the corresponding model doc page.

You can also calculate metrics on the dataset specified in your config file:

from deeppavlov import evaluate_model

model = evaluate_model(<config_path>, download=True)

There are also available integrations with various messengers, see Telegram Bot doc page and others in the Integrations section for more info.

Pretrained models

DeepPavlov provides a wide range of pretrained models and skills. See features overview for more info. Please note that most of our models are trained on specific datasets for specific tasks and may require further training on you data. You can find a list of our out-of-the-box models below.

Docker images

You can run DeepPavlov models in riseapi mode via Docker without installing DP. Both your CPU and GPU (we support NVIDIA graphic processors) can be utilised, please refer our CPU and GPU Docker images run instructions.

Out-of-the-box pretrained models

While the best way to solve most of the NLP tasks lies through collecting datasets and training models according to the domain and an actual task itself, DeepPavlov offers several pretrained models, which can be strong baselines for a wide range of tasks.

You can run these models via Docker or in riseapi/risesocket mode to use in solutions. See riseapi and risesocket modes documentation for API details.

Text Question Answering

Text Question Answering component answers a question based on a given context (e.g, a paragraph of text), where the answer to the question is a segment of the context.

Language

DeepPavlov config

Demo

Multi

squad_bert_multilingual_freezed_emb

https://demo.deeppavlov.ai/#/mu/textqa

En

squad_bert_infer

https://demo.deeppavlov.ai/#/en/textqa

Ru

squad_ru_bert_infer

https://demo.deeppavlov.ai/#/ru/textqa

Name Entity Recognition

Named Entity Recognition (NER) classifies tokens in text into predefined categories (tags), such as person names, quantity expressions, percentage expressions, names of locations, organizations, as well as expression of time, currency and others.

Language

DeepPavlov config

Demo

Multi

ner_ontonotes_bert_mult

https://demo.deeppavlov.ai/#/mu/ner

En

ner_ontonotes_bert_mult

https://demo.deeppavlov.ai/#/en/ner

Ru

ner_rus_bert

https://demo.deeppavlov.ai/#/ru/ner

Insult Detection

Insult detection predicts whether a text (e.g, post or speech in some public discussion) is considered insulting to one of the persons it is related to.

Language

DeepPavlov config

Demo

En

insults_kaggle_conv_bert

https://demo.deeppavlov.ai/#/en/insult

Sentiment Analysis

Classify text according to a prevailing emotion (positive, negative, etc.) in it.

Language

DeepPavlov config

Demo

Ru

rusentiment_elmo_twitter_cnn

https://demo.deeppavlov.ai/#/ru/sentiment

Paraphrase Detection

Detect if two given texts have the same meaning.

Language

DeepPavlov config

Demo

En

paraphraser_bert

None

Ru

paraphraser_rubert

None