DeepPavlov is an open-source framework for chatbots and virtual assistants development. It has comprehensive and flexible tools that let developers and NLP researchers create production ready conversational skills and complex multi-skill conversational assistants.
Questions tagged [deeppavlov]
30 questions
2
votes
0 answers
cannot import name 'convert_examples_to_features' deeppavlov
I tried to run the snippet of code from the tutorial about NER from deeppavlov.
Link tutorial
First I run command:
python -m deeppavlov install ner_ontonotes_bert_mult
python -m deeppavlov interact ner_ontonotes_bert_mult [-d]
Then
from deeppavlov…
Sambr The Slayer
- 21
- 2
2
votes
1 answer
How i can get probabilities in DeepPavlov classifier?
I train my classifier using DeepPavlov, and then when i call trained model for some sample function returns only one class label, but I want to get the probabilities of every class. I did not find function parameters that would allow me to get…
Iskander Safiulin
- 21
- 2
2
votes
1 answer
DeepPavlov ranking own responses
Does anybody know, how to use deeppavlov ranking module with own responses? Documentation (http://docs.deeppavlov.ai/en/master/components/neural_ranking.html) provides the following code (for insurance dataset):
rank_model =…
Norbert R
- 131
- 8
1
vote
1 answer
Running deeppavlov model in a container results in TypeError: Descriptors cannot not be created directly
I'm trying to run one of deeppavlov's models in a docker container on Windows 10, but I'm getting an error: 'TypeError: Descriptors cannot not be created directly.'
Could someone please explain what's going wrong here?
At first I typed in "docker…
Kaori
- 49
- 1
- 7
1
vote
1 answer
How can I build a custom context based Question answering model SQuAD using deeppavlov
I have the following queries
Dataset format (is how to split train, test and valid data )
Where to place the dataset
How to change the path for dataset reader
How to save the model in my own directory
And How to use the trained…
Sayak Ghanta
- 21
- 3
1
vote
1 answer
How to build 'ner_ontonotes_bert_mult' model from scratch
How can I custom train the model "ner_ontonotes_bert_mult". I want to train the model with my own dataset which have some different tags. How to train the model and use it?
When I am training my model it accepting only 40 data and after that…
Sayak Ghanta
- 21
- 3
1
vote
1 answer
DeepPavlov REST API response format is not valid JSON
I currently have a DeepPavlov bot running in a docker container and using the rise RESTAPI.
My model is based on the English Q&A bot config, but trained on my own Q/A data. It has the identical chainer config.
It ends with the…
Coreylh
- 131
- 1
- 1
- 8
1
vote
1 answer
Retrain the multi language NER model(ner_ontonotes_bert_mult) from DeepPavlov with a dataset in a different language
I have successfully installed the multi-language NER model from DeepPavlov(ner_ontonotes_bert_mult). I want to retrain this model with new data(in the same format as they suggest in the documentation page) that are in the Albanian language.Is this…
Xhensila Poda
- 13
- 1
- 3
1
vote
1 answer
deeppavlov model train no module found
I'm trying to start deeppavlov model training on GoogleColab:
with configs.ner.ner_ontonotes_bert_mult.open(encoding='utf8') as f:
nerconfig = json.load(f)
nerconfig['dataset_reader']['data_path'] =…
sigma
- 13
- 4
0
votes
0 answers
Using Camembert pre-trained model with DeepPavlov
I'm learning how to use DeepPavlov and can't figure how to use it for NER using the Camembert (french) pre-trained model. My goal is to tag a short paragraph in french.
The docs from deeppavlov explicitly list the Camembert model as a viable…
Phil
- 1
- 2
0
votes
1 answer
BERT model convertation from DeepPavlov to HuggingFace format
I have a folder with the ruBERT model, which was fine-tuned with the application of the Deeppavlov library.
The folder contains the following model files:
How do I convert it to Huggingface format so that I can load it this way?
from transformers…
senek
- 45
- 1
- 1
- 9
0
votes
1 answer
DeepPavlov error loading the model from Tensorflow (from_tf=True)
I'm trying to load the ruBERT model into Deeppavlov as follows:
#is a dict
config_path = {
"chainer": {
"in": [
"x"
],
"in_y": [
"y"
],
"out": [
"y_pred_labels",
"y_pred_probas"
…
senek
- 45
- 1
- 1
- 9
0
votes
0 answers
Error in training the model DeepPavlov DaNetQA on my own data
I'm a beginner and I'm trying to train model DaNetQA on some data in json format. E.g. one of the entries in the train.json file:
{"question": "Вднх - это выставочный центр?", "passage": "«Вы́ставочный центр» — станция Московского монорельса.",…
Yuri
- 1
- 1
0
votes
1 answer
error in building model "ner_ontonotes_bert_mult" in DeepPavlov
I'm trying to build model "ner_ontonotes_bert_mult" via GoogleColab using example in documentation:
from deeppavlov import build_model, configs
ner_model = build_model(configs.ner.ner_ontonotes_bert_mult, download=True)
but get error:
TypeError:…
Yuri
- 1
- 1
0
votes
0 answers
Alibi Explain not imported in Docker container with Deeppavlov
I'm trying to build a Docker container with the DeepPavlov image + add the Alibi Explain library to the image. I need the Deep pavlov and Alibi Explain libraries to coexist together in the same container.
Dockerfile contains the following:
FROM…
senek
- 45
- 1
- 1
- 9