https://github.com/dmis-lab/bioasq9b-dmis
KU-DMIS at BioASQ 9
https://github.com/dmis-lab/bioasq9b-dmis
Last synced: about 1 year ago
JSON representation
KU-DMIS at BioASQ 9
- Host: GitHub
- URL: https://github.com/dmis-lab/bioasq9b-dmis
- Owner: dmis-lab
- License: other
- Created: 2021-06-01T06:52:06.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2021-09-27T08:49:55.000Z (over 4 years ago)
- Last Synced: 2025-01-23T10:36:05.799Z (over 1 year ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 68.4 KB
- Stars: 4
- Watchers: 4
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## KU-DMIS at BioASQ 9: Data-centric and model-centric approaches for biomedical question answering
This repository provides supplimentary data for our participation in the 9th BioASQ challenge.
The annotation (Data-centric approach) on the training dataset of the BioASQ Challenge 8b is provided as TSV/MS excel format with example code to read the data.
Source code and models for factoid and yesno questions are available on the repogitory for our previous participations (7th and 8th; please see Quick Links section).
### Quick Links
Link | Detail
------------- | -------------
[8th BioASQ](https://github.com/dmis-lab/bioasq8b) | Code and resources for the eighth BioASQ challenge winning model (factoid/yesno/list)
[7th BioASQ](https://github.com/dmis-lab/bioasq-biobert) | Code resources for the seventh BioASQ challenge winning model (factoid/yesno/list)
[BioBERT-PyTorch](https://github.com/dmis-lab/biobert-pytorch) | PyTorch-based BioBERT implementation
[BioBERT](https://github.com/dmis-lab/biobert) | BioBERT
[BERN](https://bern.korea.ac.kr) | Web-based biomedical NER + normalization using BioBERT
### Datasets
We provide pre-processed version of BioASQ 8b - Phase B datasets for each task as follows:
* **[`BioASQ 8b`](https://drive.google.com/file/d/1THaDKpoiVRWvJjH9d0LZYakzVoBHKMI1/view?usp=sharing)** (23 MB)
Due to the copyright issue, we can not provide golden answers for BioASQ test dataset.
To use BioASQ datasets, you should register in [BioASQ website](http://participants-area.bioasq.org).
For details on the datasets, please see **An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition (Tsatsaronis et al. 2015)**.
### License and Disclaimer
Please see and agree `LICENSE` file for details. Downloading data indicates your acceptance of our disclaimer.
### Contact information
For help or issues using our model, please contact Wonjin Yoon (`wonjin.info {at} gmail.com`) for communication related to the paper.