Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Training Open Domain Question Answering Model on AzureML with DeepPavlov

Training Open Domain Question Answering Model on AzureML with DeepPavlov

D8730970396729af16546cc69ce63b44?s=128

Dmitri Soshnikov

June 23, 2020
Tweet

Transcript

  1. Training Open Domain Question Answering Model on Azure ML with

    DeepPavlov Dmitry Soshnikov, Cloud Developer Advocate, Microsoft http://soshnikov.com
  2. What is Open Domain Question Answering? Open Domain Question Answering

    – a task, when a model is able to give specific answers contained in a large volume of text (e.g. Wikipedia) - Where did guinea pigs originate? - Andes of South America - When did the Lynmouth floods happen? - 1804
  3. COVID Open Domain Question Answering - what is coronavirus? -

    respiratory tract infection - what is reproductive number? - 5.2 - Is COVID similar to SARS? - All coronaviruses share a very similar organization in their functional and structural genes https://allenai.org/data/cord-19 CORD-19 Dataset Contains over 63,000 scholarly articles about COVID-19 and the coronavirus family of viruses for use by the global research community
  4. Language Models Common tasks for NLP: • Intent Classification •

    Named Entity Recognition (NER) • Keyword Extraction • Text Summarization • Question Answering Open Domain Question Answering – a task, when a model is able to give specific answers contained in a large volume of text (e.g. Wikipedia) - Where did guinea pigs originate? - Andes of South America - When did the Lynmouth floods happen? - 1804 Neural Language Models: • Recurrent Neural Network (RNN) • LSTM, GRU • Transformers • GPT-2 • BERT • Microsoft Turing-NLG
  5. How BERT Works (Simplified) Masked Language Model + Next Sentence

    Prediction During holidays, I like to ______ with my dog. It is so cute. 0.85 Play 0.05 Sleep 0.09 Fight 0.80 YES 0.20 NO BERT contains 345 million parameters => very difficult to train from scratch! In most of the cases it makes sense to use pre-trained language model.
  6. Text Processing Pipelines BERT for Classification Input Text BERT Features

    Classifier BERT for Entity Extraction Input Text BERT Features Mask Generator Class Prob Vector Entity Masks BERT for Question Answering Input Text BERT Features Bounds Generator Answer Bounds 0.85 Insult 0.15 Neutral I live in France My age is 21 LOC
  7. DeepPavlov: “Keras” for NLP, developed at MIPT http://deeppavlov.ai $ pip

    install deeppavlov python -m deeppavlov install config.json python -m deeppavlov download config.json python -m deeppavlov train config .json Text processing pipeline is defined in JSON config: • Processing steps, their inputs and outputs • Weight location for pre-trained models • Data shape and location • Training parameters
  8. Case Study: Intent Classification config = { ... } "dataset_reader":

    { "class_name": "basic_classification_reader", "x": "text", "y": "intents", "data_path": "./snips"}, "dataset_iterator": { "class_name": "basic_classification_iterator", "field_to_split": "train", "split_fields": ["train","valid"]}, "chainer": { "in": ["x"], "in_y": ["y"], "out": ["y_pred"], "pipe": [ ... ] } Sample on github "train": { "batch_size": 64, "metrics": ["accuracy"] } Add Live from Aragon Ballroom to Trapeo, AddToPlaylist add Unite and Win to my night out, AddToPlaylist Add track to my Digster Future Hits, AddToPlaylist add the piano bar to my Cindy Wilson, AddToPlaylist text intents
  9. Pipeline "chainer": { "in": ["x"], "in_y": ["y"], "out": ["y_pred"], "pipe":

    [ ... ] } { "id": "classes_vocab", "class_name": "simple_vocab", "fit_on": ["y"], "in": "y", "out": "y_ids" } { "in": ["x"], "out": ["x_vec"], "fit_on": ["x","y_ids"], "id": "tfidf_vec", "class_name": "sklearn_component", "model_class": "sklearn.feature_ extraction.text:TfidfVectorizer", "infer_method": "transform" } { "in": ["x_vec"], "out": ["y_pred"], "fit_on": ["x_vec","y"], "class_name": "sklearn_component", "main": True, "model_class": "sklearn.linear_model : LogisticRegression", "infer_method": "predict" } Classes_ vocab Dataset TFIDF Vectorizer Add Live from Aragon Ballroom to Trapeo, AddToPlaylist add Unite and Win to my night out, AddToPlaylist Add track to my Digster Future Hits, AddToPlaylist add the piano bar to my Cindy Wilson, AddToPlaylist Logistic Regression x y y_ids x_vec y_pred x y
  10. Open Domain Question Answering with DeepPavlov http://aka.ms/deeppavlov

  11. Starting with Azure Machine Learning Read my blog series: •

    The best way to start with Azure ML using VS Code • Using Azure ML for Hyperparameter Optimization • Training GAN to Produce Art • Training BERT Question Answering with DeepPavlov ❶ ❷ Try it out: http://github.com/CloudAdvocacy/AzureMLStarter
  12. AI / Machine Learning on Azure Domain specific pretrained models

    To reduce time to market Azure Databricks Machine Learning VMs Popular frameworks To build advanced deep learning solutions TensorFlow Pytorch Onnx Azure Machine Learning Language Speech … Search Vision Productive services To empower data science and development teams Powerful infrastructure To accelerate deep learning Scikit-Learn PyCharm Jupyter Familiar Data Science tools To simplify model development Visual Studio Code Command line CPU GPU FPGA From the Intelligent Cloud to the Intelligent Edge
  13. Where does Azure ML fit? Data Science VM Azure ML

    Cognitive Services Infrastructure services Platform Services Pre-trained Models For beginners Advanced Data Science Experimentation
  14. Simplest Way to Start with Azure ML Azure ML for

    VS Code Portal http://portal.azure.com
  15. Azure ML Workspace: A container for Everything Azure ML Workspace

    encapsulates it all: 1. Storage 2. Datasets 3. Compute 4. Notebooks 5. Experiment Results 6. Models 7. Deployments ❶ az extension add -n azure-cli-ml az group create -n ml -l westus2 az ml workspace create -w AzML -g ml az ml folder attach -w AzML -g ml Create Workspace using Azure CLI: az ml computetarget create amlcompute -n cpu --min-nodes 0 --max-nodes 2 -s STANDARD_D3_V2 Create Cluster using Azure CLI: MS Docs: HERE
  16. None
  17. Azure ML service Workspace Taxonomy

  18. Submit and Track Experiments Experiment is represented by a Python

    Script + Environment that run on Compute (Local Compute, Azure ML Cluster or Databricks) 1. Auto-package code 2. Keep track of results 3. Store models 4. Queue runs 5. Programmatically spawn many runs with different parameters ❷ az ml run submit-script -c sklearn –e MyExp train.py Submit Experiment using CLI: Log Metrics in the script: from azureml.core.run import Run run = Run.get_submitted_run() run.log('accuracy', acc)
  19. None
  20. My Computer Data Store Azure ML Workspace Compute Target Docker

    Image How Azure ML Experimentation Works Experiment
  21. Run Notebooks and Create Datasets When you do a lot

    of training, it makes sense to store data inside the workspace. To run Python code inside the workspace – use Notebooks! You need to create separate compute (not cluster) to do that! ❸
  22. None
  23. Using Azure ML to Train the ODQA Model We will

    use the following features of Azure ML: • Define file dataset that points to data location • Create cheap non-GPU compute for data exploration and preparation • Use GPU-enabled compute on the same data to train the model • All code would be in the form of Jupyter Notebooks We do not use training on Azure ML Cluster in this case to have better control on the environment. DeepPavlov downloads large amounts of pre-trained data from the network, and for simple cases it is better to use single node. Link to the non-commercial CORD-19 dataset: here (.tar.gz)
  24. Getting Wikipedia ODQA Up and Running import sys !{sys.executable} -m

    pip install deeppavlov !{sys.executable} -m deeppavlov install en_odqa_infer_wiki !{sys.executable} -m deeppavlov download en_odqa_infer_wiki from deeppavlov import configs from deeppavlov.core.commands.infer import build_model odqa = build_model(configs.odqa.en_odqa_infer_wiki) answers = odqa([ "Where did guinea pigs originate?", "When did the Lynmouth floods happen?" ]) # Get the Library and Required Models # Build Model from Config and Run Inference ['Andes of South America', '1804']
  25. ODQA Configs Ranker en_ranker_tdifd_wiki SQuAD multi_squad_noans_infer (R-NET) Config on GitHub

    en_odqa_infer_wiki question question document answer TRAIN Replace with BERT
  26. Train the Ranker from deeppavlov.core.common.file import read_json model_config = read_json(configs.doc_retrieval.en_ranker_tfidf_wiki)

    model_config["dataset_reader"]["data_path"] = os.path.join(os.getcwd(),"text") model_config["dataset_reader"]["dataset_format"] = "txt" model_config["train"]["batch_size"] = 1000 # Specify Data Path & Format doc_retrieval = train_model(model_config) doc_retrieval(['hydroxychloroquine']) # Train the Model and See the Results "dataset_reader": { "class_name": "odqa_reader", "data_path": "{DOWNLOADS_PATH}/odqa/enwiki", "save_path": "{DOWNLOADS_PATH}/odqa/enwiki.db", "dataset_format": "wiki" } Part of en_ranker_tfidf_wiki config
  27. Results with R-NET Question Answering squad = build_model(configs.squad.multi_squad_noans_infer, download =

    True) # Do not download the ODQA models, we've just trained it odqa = build_model(configs.odqa.en_odqa_infer_wiki, download = False) odqa(["what is coronavirus?","is hydroxychloroquine suitable?"]) ['an imperfect gold standard for identifying King County influenza admissions', 'viral hepatitis']
  28. Use BERT for QA # Download Pre-trained BERT Q&A Model

    # Replace Q&A Model in the Master Config Part of en_odqa_infer_wiki config !{sys.executable} -m deeppavlov install squad_bert_infer bsquad = build_model(configs.squad.squad_bert_infer, download = True) odqa_config = read_json(configs.odqa.en_odqa_infer_wiki) odqa_config['chainer']['pipe'][-1]['squad_model']['config_path'] = '{CONFIGS_PATH}/squad/squad_bert_infer.json' odqa = build_model(odqa_config, download = False) odqa(["what is coronavirus?", "is hydroxychloroquine suitable?", "which drugs should be used?"]) # Build and Use Model { "class_name": "logit_ranker", "squad_model": {"config_path": ".../multi_squad_noans_infer.json"} "in": ["chunks","questions"], "out": ["best_answer","best_answer_score"] }
  29. Question Answer what is coronavirus? respiratory tract infection is hydroxychloroquine

    suitable? well tolerated which drugs should be used? antibiotics, lactulose, probiotics what is incubation period? 3-5 days how to contaminate virus? helper-cell-based rescue system cells what is coronavirus type? enveloped single stranded RNA viruses what are covid symptoms? insomnia, poor appetite, fatigue, and attention deficit what is reproductive number? 5.2 what is the lethality? 10% where did covid-19 originate? uveal melanocytes is antibiotics therapy effective? less effective what are effective drugs? M2, neuraminidase, polymerase, attachment and signal-transduction inhibitors what is effective against covid? Neuraminidase inhibitors is covid similar to sars? All coronaviruses share a very similar organization in their functional and structural genes what is covid similar to? thrombogenesis Results
  30. Conclusions ML can be used for medical text mining: •

    Smart search on paper corpus • Clustering papers based on terminology / semantics • Trend monitoring • Automatic summarization ❶ ❷ Try out Azure Machine Learning: • http://github.com/CloudAdvocacy/AzureMLStarter • http://aka.ms/azmlstarter - Blog Post
  31. Further Reading  How to train your own neural network

    to generate paintings http://aka.ms/azml_gan  Can AI be creative http://aka.ms/creative_ai  Creating interactive exhibit based on cognitive portraits http://aka.ms/cognitive_portrait_exhibit  Training COVID ODQA on Azure ML: http://aka.ms/deeppavlov
  32. © Copyright Microsoft Corporation. All rights reserved. @art_of_artificial