jimfleming / Recurrent Entity Networks
Licence: mit
TensorFlow implementation of "Tracking the World State with Recurrent Entity Networks".
Stars: ✭ 276
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Recurrent Entity Networks
Named Entity Recognition
name entity recognition with recurrent neural network(RNN) in tensorflow
Stars: ✭ 20 (-92.75%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Simplednn
SimpleDNN is a machine learning lightweight open-source library written in Kotlin designed to support relevant neural network architectures in natural language processing tasks
Stars: ✭ 81 (-70.65%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Reading comprehension tf
Machine Reading Comprehension in Tensorflow
Stars: ✭ 37 (-86.59%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Zhihu
This repo contains the source code in my personal column (https://zhuanlan.zhihu.com/zhaoyeyu), implemented using Python 3.6. Including Natural Language Processing and Computer Vision projects, such as text generation, machine translation, deep convolution GAN and other actual combat code.
Stars: ✭ 3,307 (+1098.19%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Rnn lstm from scratch
How to build RNNs and LSTMs from scratch with NumPy.
Stars: ✭ 156 (-43.48%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Keras Attention
Visualizing RNNs using the attention mechanism
Stars: ✭ 697 (+152.54%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Chicksexer
A Python package for gender classification.
Stars: ✭ 64 (-76.81%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Ner Lstm
Named Entity Recognition using multilayered bidirectional LSTM
Stars: ✭ 532 (+92.75%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Deep Lyrics
Lyrics Generator aka Character-level Language Modeling with Multi-layer LSTM Recurrent Neural Network
Stars: ✭ 127 (-53.99%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Pytorch Pos Tagging
A tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.
Stars: ✭ 96 (-65.22%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Sangita
A Natural Language Toolkit for Indian Languages
Stars: ✭ 43 (-84.42%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Pytorch Sentiment Analysis
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+1062.68%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Multitask sentiment analysis
Multitask Deep Learning for Sentiment Analysis using Character-Level Language Model, Bi-LSTMs for POS Tag, Chunking and Unsupervised Dependency Parsing. Inspired by this great article https://arxiv.org/abs/1611.01587
Stars: ✭ 93 (-66.3%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Attention Mechanisms
Implementations for a family of attention mechanisms, suitable for all kinds of natural language processing tasks and compatible with TensorFlow 2.0 and Keras.
Stars: ✭ 203 (-26.45%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Awesome Tensorlayer
A curated list of dedicated resources and applications
Stars: ✭ 248 (-10.14%)
Mutual labels: natural-language-processing, recurrent-neural-networks
Ai Job Notes
AI算法岗求职攻略（涵盖准备攻略、刷题指南、内推和AI公司清单等资料）
Stars: ✭ 3,191 (+1056.16%)
Mutual labels: natural-language-processing
Nlpython
This repository contains the code related to Natural Language Processing using python scripting language. All the codes are related to my book entitled "Python Natural Language Processing"
Stars: ✭ 265 (-3.99%)
Mutual labels: natural-language-processing
Da Rnn
📃 **Unofficial** PyTorch Implementation of DA-RNN (arXiv:1704.02971)
Stars: ✭ 256 (-7.25%)
Mutual labels: recurrent-neural-networks
Fakenewscorpus
A dataset of millions of news articles scraped from a curated list of data sources.
Stars: ✭ 255 (-7.61%)
Mutual labels: natural-language-processing
Easy Tensorflow
Simple and comprehensive tutorials in TensorFlow
Stars: ✭ 2,871 (+940.22%)
Mutual labels: recurrent-neural-networks
Recurrent Entity Networks
This repository contains an independent TensorFlow implementation of recurrent entity networks from Tracking the World State with Recurrent Entity Networks. This paper introduces the first method to solve all of the bAbI tasks using 10k training examples. The author's original Torch implementation is now available here.
Results
Percent error for each task, comparing those in the paper to the implementation contained in this repository.
| Task | EntNet (paper) | EntNet (repo) |
|---|---|---|
| 1: 1 supporting fact | 0 | 0 |
| 2: 2 supporting facts | 0.1 | 3.0 |
| 3: 3 supporting facts | 4.1 | ? |
| 4: 2 argument relations | 0 | 0 |
| 5: 3 argument relations | 0.3 | ? |
| 6: yes/no questions | 0.2 | 0 |
| 7: counting | 0 | 0 |
| 8: lists/sets | 0.5 | 0 |
| 9: simple negation | 0.1 | 0 |
| 10: indefinite knowledge | 0.6 | 0 |
| 11: basic coreference | 0.3 | 0 |
| 12: conjunction | 0 | 0 |
| 13: compound coreference | 1.3 | 0 |
| 14: time reasoning | 0 | 0 |
| 15: basic deduction | 0 | 0 |
| 16: basic induction | 0.2 | 0 |
| 17: positional reasoning | 0.5 | 1.7 |
| 18: size reasoning | 0.3 | 1.5 |
| 19: path finding | 2.3 | 0 |
| 20: agents motivation | 0 | 0 |
| Failed Tasks | 0 | ? |
| Mean Error | 0.5 | ? |
NOTE: Some of these tasks (16 and 19, in particular) required a change in learning rate schedule to reliably converge.
Setup
- Download the datasets by running download_babi.sh or from The bAbI Project.
- Run prep_data.py which will convert the datasets into TFRecords.
- Run
python -m entity_networks.mainto begin training on QA1.
Major Dependencies
- TensorFlow v1.1.0
(For additional dependencies see requirements.txt)
Thanks!
- Thanks to Mikael Henaff for providing details about their paper over Thanksgiving break. :)
- Thanks to Andy Zhang (@zhangandyx) for helping me troubleshoot numerical instabilities.
- Thanks to Mike Young (@mikalyoung) for providing results on some of the longer tasks.
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].