localminimum/QANet
A TensorFlow implementation of QANet for machine reading comprehension on the SQuAD dataset.
Not currently ranked — collecting fresh signals.
star history
This repository provides a TensorFlow implementation of QANet, a neural network architecture for machine reading comprehension introduced at ICLR 2018. The model processes questions and passages to extract answers, using convolutional encoders with self-attention rather than recurrent layers for faster inference. Training uses the Stanford Question Answering Dataset with GloVe word embeddings, and achieves EM/F1 scores around 70.8/80.1 after 60k training steps.
Frequently asked
- What is localminimum/QANet?
- A TensorFlow implementation of QANet for machine reading comprehension on the SQuAD dataset.
- Is QANet open source?
- Yes — localminimum/QANet is open source, released under the MIT license.
- What language is QANet written in?
- localminimum/QANet is primarily written in Python.
- How popular is QANet?
- localminimum/QANet has 984 stars on GitHub.
- Where can I find QANet?
- localminimum/QANet is on GitHub at https://github.com/localminimum/QANet.