DeepPavlov
DeepPavlov copied to clipboard
An open source library for deep learning end-to-end dialog systems and chatbots.
Want to contribute to DeepPavlov? Please read the [contributing guideline](http://docs.deeppavlov.ai/en/master/devguides/contribution_guide.html) first. **What problem are we trying to solve?**: ``` There is no documentation or docstrings for these metrics. ``` **How...
For now learning rate scheduling is implemented using the [LRScheduledModel](https://github.com/deepmipt/DeepPavlov/blob/613d265f7371ba05365a7d44485066293c169674/deeppavlov/core/models/lr_scheduled_model.py#L129-L132) class and its inheritors. It would be great to move this logic to a trainer class inherited from the [NNTrainer](https://github.com/deepmipt/DeepPavlov/blob/613d265f7371ba05365a7d44485066293c169674/deeppavlov/core/trainers/nn_trainer.py#L33-L38)...
Suppose I have the attribute containing a list of strings `list_of_strings` in the component `component1` and I would like to pass it to the next component in the pipe `component2`...
I run this code: from deeppavlov import configs from deeppavlov.core.common.file import read_json from deeppavlov import configs, train_model model_config = read_json(configs.doc_retrieval.en_ranker_tfidf_wiki) model_config["dataset_reader"]["data_path"] = "SentenceCorpus/unlabeled_articles/plos_unlabeled" model_config["dataset_reader"]["dataset_format"] = "txt" model_config["dataset_reader"]["save_path"] = "odqa/enwiki.db" model_config["dataset_iterator"]["load_path"]...
When I use dataset_format txt, the training fails because of the DS_Store system file, maybe it would be good to add exceptions for all operating systems. ` rika@MacBook-Pro adp %...
Hi! I have a gobot, based on dstc2 gobot example. gobot.json references to slofiller.json and slotfiller.json references to ner.json. There is a problem of embedders duplicating (one for ner and...
The biggest issue I am facing in creation of training data for go-bot is creation of new intents. Here is something I would like to suggest:- 1.) Apply Sequence to...
I think that the researchers who need morphological analysis in their tasks may be split up into two groups: 1) those who need only lemmatizer (for dimension reduction etc.); 2)...
Why don't throw a warning in case of one-label classification if exists in classes and prevents roc_auc calculation?
Меня интересует повышение доли правильно лемматизированных санскритизмов (санскритских слов в кириллической записи) в русском языке с помощью морфологического анализа deeppavlov. Хуже всего анализатор справился с определением леммы слов и показал...