#132 · Primary category： NLP Tools & Text Processing
QANet
A Tensorflow implementation of QANet for machine reading comprehension
Project last updated：05/30/18
GitHub Stars
985
Forks
297
Contributors
5
License
MIT
Why we included this project
If the original QANet paper left you wanting a concrete implementation to study, this community TensorFlow port delivers one. The author documented the compromises made to fit training on a single 8GB GPU, including a single attention head and a reduced hidden size, and reports EM/F1 of 70.8/80.1 at 60k steps so you can see how those changes affect accuracy. The repository includes a complete pipeline that downloads SQuAD, preprocesses the data, trains the model, runs official evaluation, and launches an interactive demo server. That makes it a useful starting point for reproducing an extractive QA system or as a baseline to test your own ideas against.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
compromise
modest natural-language processing
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
CoreNLP
CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.
Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量