PyText
master

Getting Started

  • Installation
  • Train your first model
  • Execute your first model
  • Visualize Model Training with TensorBoard
  • Use PyText models in your app
  • Serve Models in Production
  • Config Files Explained
  • Config Commands

Training More Advanced Models

  • Train Intent-Slot model on ATIS Dataset
  • Hierarchical intent and slot filling
  • Multitask training with disjoint datasets
  • Data Parallel Distributed Training
  • XLM-RoBERTa
  • Semantic parsing with sequence-to-sequence models

Extending PyText

  • Architecture Overview
  • Custom Data Format
  • Custom Tensorizer
  • Using External Dense Features
  • Creating A New Model
  • Hacking PyText

References

  • pytext
    • config
    • data
    • exporters
    • loss
    • metric_reporters
    • models
      • bert_classification_models
      • bert_regression_model
      • decoders
      • disjoint_multitask_model
      • doc_model
      • embeddings
      • ensembles
      • joint_model
      • language_models
      • masked_lm
      • model
      • module
      • output_layers
      • pair_classification_model
      • qna
      • query_document_pairwise_ranking_model
      • r3f_models
      • representations
        • attention
        • augmented_lstm
        • bilstm
        • bilstm_doc_attention
        • bilstm_doc_slot_attention
        • bilstm_slot_attn
        • biseqcnn
        • contextual_intent_slot_rep
        • deepcnn
        • docnn
        • huggingface_bert_sentence_encoder
        • huggingface_electra_sentence_encoder
        • jointcnn_rep
        • ordered_neuron_lstm
        • pass_through
        • pooling
        • pure_doc_attention
        • representation_base
        • seq_rep
        • slot_attention
        • sparse_transformer_sentence_encoder
        • stacked_bidirectional_rnn
        • transformer
        • transformer_sentence_encoder
        • transformer_sentence_encoder_base
      • roberta
      • semantic_parsers
      • seq_models
      • two_tower_classification_model
      • word_model
    • optimizer
    • task
    • torchscript
    • trainers
  • pytext package
PyText
  • Docs »
  • pytext »
  • models »
  • representations
  • Edit on GitHub

representationsΒΆ

  • attention
    • DotProductSelfAttention.Config
    • MultiplicativeAttention.Config
    • SequenceAlignedAttention.Config
  • augmented_lstm
    • AugmentedLSTM.Config
  • bilstm
    • BiLSTM.Config
  • bilstm_doc_attention
    • BiLSTMDocAttention.Config
  • bilstm_doc_slot_attention
    • BiLSTMDocSlotAttention.Config
  • bilstm_slot_attn
    • BiLSTMSlotAttention.Config
  • biseqcnn
    • BSeqCNNRepresentation.Config
  • contextual_intent_slot_rep
    • ContextualIntentSlotRepresentation.Config
  • deepcnn
    • DeepCNNRepresentation.Config
  • docnn
    • DocNNRepresentation.Config
  • huggingface_bert_sentence_encoder
    • HuggingFaceBertSentenceEncoder.Config
  • huggingface_electra_sentence_encoder
    • HuggingFaceElectraSentenceEncoder.Config
  • jointcnn_rep
    • JointCNNRepresentation.Config
    • SharedCNNRepresentation.Config
  • ordered_neuron_lstm
    • OrderedNeuronLSTM.Config
    • OrderedNeuronLSTMLayer.Config
  • pass_through
    • PassThroughRepresentation.Config
  • pooling
    • BoundaryPool.Config
    • LastTimestepPool.Config
    • MaxPool.Config
    • MeanPool.Config
    • NoPool.Config
    • SelfAttention.Config
  • pure_doc_attention
    • PureDocAttention.Config
  • representation_base
    • RepresentationBase.Config
  • seq_rep
    • SeqRepresentation.Config
  • slot_attention
    • SlotAttention.Config
  • sparse_transformer_sentence_encoder
    • SparseTransformerSentenceEncoder.Config
  • stacked_bidirectional_rnn
    • StackedBidirectionalRNN.Config
  • transformer
    • representation
      • TransformerRepresentation.Config
  • transformer_sentence_encoder
    • TransformerSentenceEncoder.Config
  • transformer_sentence_encoder_base
    • TransformerSentenceEncoderBase.Config
Next Previous

© Copyright 2018, PyText Contributors Revision e407685a.

Built with Sphinx using a theme provided by Read the Docs.