All Projects → flrngel → Self Attentive Tensorflow

flrngel / Self Attentive Tensorflow

Tensorflow implementation of "A Structured Self-Attentive Sentence Embedding"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Self Attentive Tensorflow

Fastpunct
Punctuation restoration and spell correction experiments.
Stars: ✭ 121 (-35.98%)
Mutual labels:  attention
Multihead Siamese Nets
Implementation of Siamese Neural Networks built upon multihead attention mechanism for text semantic similarity task.
Stars: ✭ 144 (-23.81%)
Mutual labels:  attention
Rnn For Joint Nlu
Pytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling" (https://arxiv.org/abs/1609.01454)
Stars: ✭ 176 (-6.88%)
Mutual labels:  attention
Absa keras
Keras Implementation of Aspect based Sentiment Analysis
Stars: ✭ 126 (-33.33%)
Mutual labels:  attention
Vqa regat
Research Code for ICCV 2019 paper "Relation-aware Graph Attention Network for Visual Question Answering"
Stars: ✭ 129 (-31.75%)
Mutual labels:  attention
Hey Jetson
Deep Learning based Automatic Speech Recognition with attention for the Nvidia Jetson.
Stars: ✭ 161 (-14.81%)
Mutual labels:  attention
Nlp Models Tensorflow
Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0
Stars: ✭ 1,603 (+748.15%)
Mutual labels:  attention
Datastories Semeval2017 Task4
Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".
Stars: ✭ 184 (-2.65%)
Mutual labels:  attention
Prediction Flow
Deep-Learning based CTR models implemented by PyTorch
Stars: ✭ 138 (-26.98%)
Mutual labels:  attention
Attentionn
All about attention in neural networks. Soft attention, attention maps, local and global attention and multi-head attention.
Stars: ✭ 175 (-7.41%)
Mutual labels:  attention
Asr syllable
基于卷积神经网络的语音识别声学模型的研究
Stars: ✭ 127 (-32.8%)
Mutual labels:  attention
Image Caption Generator
A neural network to generate captions for an image using CNN and RNN with BEAM Search.
Stars: ✭ 126 (-33.33%)
Mutual labels:  attention
Multimodal Sentiment Analysis
Attention-based multimodal fusion for sentiment analysis
Stars: ✭ 172 (-8.99%)
Mutual labels:  attention
Ccnet Pure Pytorch
Criss-Cross Attention for Semantic Segmentation in pure Pytorch with a faster and more precise implementation.
Stars: ✭ 124 (-34.39%)
Mutual labels:  attention
Pyramid Attention Networks Pytorch
Implementation of Pyramid Attention Networks for Semantic Segmentation.
Stars: ✭ 182 (-3.7%)
Mutual labels:  attention
Sightseq
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (-38.62%)
Mutual labels:  attention
Medical Transformer
Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation"
Stars: ✭ 153 (-19.05%)
Mutual labels:  attention
Graph attention pool
Attention over nodes in Graph Neural Networks using PyTorch (NeurIPS 2019)
Stars: ✭ 186 (-1.59%)
Mutual labels:  attention
Deep Time Series Prediction
Seq2Seq, Bert, Transformer, WaveNet for time series prediction.
Stars: ✭ 183 (-3.17%)
Mutual labels:  attention
Transformers.jl
Julia Implementation of Transformer models
Stars: ✭ 173 (-8.47%)
Mutual labels:  attention

Self-Attentive-Tensorflow

model image of Self Attentive

Tensorflow implementation of A Structured Self-Attentive Sentence Embedding

You can read more about concept from this paper

Key Concept

Frobenius norm with attention

Usage

Download ag news dataset as below

$ tree ./data
./data
└── ag_news_csv
    ├── classes.txt
    ├── readme.txt
    ├── test.csv
    ├── train.csv
    └── train_mini.csv

and then

$ python train.py

Result

Accuracy 0.895

visualize without penalization

visualize with penalization

To-do list

  • support multiple dataset

Notes

This implementation does not use pretrained GloVe or Word2vec.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].