Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
14H034160212 authored Jul 18, 2022
1 parent ed55573 commit 3633a9b
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,10 @@
This repository contains the code for the paper "Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation". This paper is the extention work from the poster [From Symbolic Logic Reasoning to Soft Reasoning: A Neural-Symbolic Paradigm](https://www.researchgate.net/publication/356695884_From_Symbolic_Logic_Reasoning_to_Soft_Reasoning_A_Neural-Symbolic_Paradigm). We add details for building the large-scale deeper multi-step reasoning dataset PARARULE-Plus and more experiments by adding the PARARULE-Plus in training. The goal is to build up an end-to-end neural based reasoning engine. The existing neural based models lack a reasoning engine, and they are not end-to-end training process. The repository also incorporates extra code for research as part of future work.

## Dataset
All the current work data is using the [PARARULE](https://allenai.org/data/ruletaker) from Allen AI institute. The dataset has been published on [Transformers as Soft Reasoners over Language](https://arxiv.org/abs/2002.05867), [CONCEPTRULES V1](https://drive.google.com/file/d/1lxoAvtcvqVCYiO8e3tENnrTQ1NNVtpjs/view?usp=sharing) and [CONCEPTRULES V2](https://drive.google.com/file/d/1lOCbW8bfZxj1RIzKDxn8xKg99XyYNj7z/view?usp=sharing) from [Tim Hartill](https://github.com/timhartill) and [PARARULE-Plus](https://github.com/Strong-AI-Lab/PARARULE-Plus). You can download the data from the `data` folder.
All the current work data is using the [PARARULE](https://allenai.org/data/ruletaker) from Allen AI institute. The dataset has been published on [Transformers as Soft Reasoners over Language](https://arxiv.org/abs/2002.05867), [CONCEPTRULES V1](https://drive.google.com/file/d/1lxoAvtcvqVCYiO8e3tENnrTQ1NNVtpjs/view?usp=sharing) and [CONCEPTRULES V2](https://drive.google.com/file/d/1lOCbW8bfZxj1RIzKDxn8xKg99XyYNj7z/view?usp=sharing) from [Tim Hartill](https://github.com/timhartill) and [PARARULE-Plus](https://github.com/Strong-AI-Lab/PARARULE-Plus). You can download the data from the `dataset` folder.

## Code
The main body of the code is following with my previous project [From Symbolic Logic Reasoning to Soft Reasoning: A Neural-Symbolic Paradigm](https://github.com/Strong-AI-Lab/A-Neural-Symbolic-Paradigm). We add more experiment analysis on CONCEPTRULES V1 CONCEPTRULE V2, and PARARULE-Plus. You can look and use the code in the `source code` folder.
The main body of the code is following with my previous project [From Symbolic Logic Reasoning to Soft Reasoning: A Neural-Symbolic Paradigm](https://github.com/Strong-AI-Lab/A-Neural-Symbolic-Paradigm). We add more experiment analysis on CONCEPTRULES V1, CONCEPTRULE V2, and PARARULE-Plus. You can look and use the code in the `source code` folder.

## Citation
```
Expand Down

0 comments on commit 3633a9b

Please sign in to comment.