Improving Question Answering Performance Using Knowledge Distillation and Active Learning
-
Updated
Mar 13, 2024 - Python
Improving Question Answering Performance Using Knowledge Distillation and Active Learning
a implementation of google QAnet, a tensorflow estimator version, have very good proved performance
We implemented QANet from scratch and improved baseline BiDAF. We also used an ensemble of BiDAF and QANet models to achieve EM/F1 of 69.47/71.96, ranking #3 on the leaderboard as of Mar 4, 2022.
State of the art of Neural Question Answering using PyTorch.
Tensorflow implementation and pre-trained models of QANet for machine reading comprehension
Important paper implementations for Question Answering using PyTorch
A Tensorflow implementation of QANet for machine reading comprehension on Chinese corpus.
Machine Reading Comprehension in Tensorflow
Using QANet and BiDAF on DuReader datasets
Includes implementations of various Question-Answering models for the SQuAD dataset and other Research Experiments
Tensorflow QANet with ELMo
A TensorFlow implementation of Google's QANet (https://openreview.net/pdf?id=B14TlG-RW)
Add a description, image, and links to the qanet topic page so that developers can more easily learn about it.
To associate your repository with the qanet topic, visit your repo's landing page and select "manage topics."