State of the art of Neural Question Answering using PyTorch.

ML Projects and Experience in Industry and Academia.

BiDAF reading comprehension model with Answer Pointer head.

Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.

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.

Bidirectional Attention Flow for Machine Comprehension implemented in Keras 2

Answering a query about a given context paragraph using a model based on recurrent neural networks and attention.

This is BIDAF mechanism based question answering network implementation without using and pretrained language representations.

Pytorch实现Bidaf基于原文提取的机器阅读理解算法

Implementation of the Bi-Directional Attention Flow Model (BiDAF) in Python using Keras

Question answering on the SQuAD dataset, for NLP class at UNIBO

Important paper implementations for Question Answering using PyTorch

Implementation of the machine comprehension model in our ACL 2019 paper: Augmenting Neural Networks with First-order Logic.

Question Answering System using BiDAF Model on SQuAD v2.0

Implementation of Bidirectional Attention Flow as illustrated in the paper from Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, Hannaneh Hajishirzi

Implementing the Bidirectional Attention Flow model using pytorch

Bi-Directional Attention Flow (BiDAF) question answering model enhanced by multi-layer convolutional neural network character embeddings.

Machine Reading Comprehension in Tensorflow

tf bidaf and qanet for dureader dataset

Using QANet and BiDAF on DuReader datasets