torch-teacher
torch-teacher copied to clipboard
Published
20 hours ago •
ganeshjawahar
ganeshjawahar
Compilation of the state-of-the-art neural models used in Machine Reading and Comprehension Task (in progress)
Teaching Machines to Read and Comprehend CNN News and Children Books using Torch
This software repository hosts the self-contained implementation of the state-of-the-art models used in Machine Reading and Comprehension Task.
| Folder | Reference |
|---|---|
| watson/ | Text Understanding with the Attention Sum Reader Network, Kadlec et al., ACL 2016. |
| stanford/ | A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task, Chen et al., ACL 2016. |
| fair/ | The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations, Hill et al., ICLR 2016. |
Benchmarking Training Time
| mins per batch (mins per epoch) | watson/ | stanford/ | fair/ |
|---|---|---|---|
| GPU\Batch Size | 32 | 32 | 1 |
| K40 | 806 ms (46m 16s) |
800 ms (2h 40m) |
18ms (34m 8s) |
| Titan X | 746 ms (42m 38s) |
- | 13ms (24m 45s) |
| 1080 | 889 ms (51m 8s) |
- | 13ms (25m 29s) |
Acknowledgements
This repository would not be possible without the efforts of the maintainers of the following libraries:
- Element-Research/rnn
- MemNN
- Torch (Ofcourse!)
Author
Licence
MIT
Metadata
44
Stars
10
Forks
Watchers
Owner
ganeshjawahar
Metadata
Compilation of the state-of-the-art neural models used in Machine Reading and Comprehension Task (in progress)