Thesis/ADNC
1
0
Fork 0
mirror of https://github.com/JoergFranke/ADNC.git synced 2024-11-17 13:58:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

update README with links

Browse Source
This commit is contained in:
joergfranke 2018-07-10 16:12:50 +02:00
parent 098b44ac51
commit caf9e137fa
1 changed files with 22 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
README.md
View File

@ -7,15 +7,31 @@
*This repository is under construction and some comments and functions are missing.* *This repository is under construction and some comments and functions are missing.*
This repository contains a implementation of a Differentiable Neural Computer (DNC) with advancements for a more robust and This repository contains a implementation of a Differentiable Neural Computer (DNC) with advancements for a more robust and
scalable usage in Question Answering. It is applied to: scalable usage in Question Answering. It is published on the MRQA workshop at the ACL 2018.
- MRQA 2018 paper submission [Robust and Scalable Differentiable Neural Computer for Question Answering](https://arxiv.org/abs/1807.02658)
- More detailed master thesis about the [Advanced DNC for Question Answering](http://isl.anthropomatik.kit.edu/cmu-kit/downloads/Master_Franke_2018.pdf)
The ADNC is applied to:
- [20 bAbI QA tasks](https://research.fb.com/downloads/babi/) with [state-of-the-art results](#babi-results) - [20 bAbI QA tasks](https://research.fb.com/downloads/babi/) with [state-of-the-art results](#babi-results)
- [CNN Reading Comprehension Task](https://github.com/danqi/rc-cnn-dailymail) with - [CNN Reading Comprehension Task](https://github.com/danqi/rc-cnn-dailymail) with
[passable results](#cnn-results) without any adaptation or hyper-parameter tuning. [passable results](#cnn-results) without any adaptation or hyper-parameter tuning.
This repository is the groundwork for the MRQA 2018 The implementation provides the following features:
paper submission "Robust and Scalable Differentiable Neural Computer for Question Answering". It contains a modular and
fully configurable DNC with the following advancements:
- Multi-read and multi-write head memory units
- Key implementations (memory unit, controller, etc. ) have tests
- Modular implementation of memory unit and controller
- Fully configurable by a yaml-file
- Pre-trained models on bAbI task and CNN RC task
- Plot of the memory unit functionality during inference
- The following advancements are implemented:
<!--
This repository is the groundwork for the MRQA 2018
paper submission [Robust and Scalable Differentiable Neural Computer for Question Answering](https://arxiv.org/abs/1807.02658). It contains a modular and
fully configurable DNC with the following advancements: -->
<table> <table>