https://github.com/straymat/bio-medical_ner
This repo contains all data and code necessary to reproduce the experiments of ner on some open bio-medical corpora
https://github.com/straymat/bio-medical_ner
Last synced: 5 months ago
JSON representation
This repo contains all data and code necessary to reproduce the experiments of ner on some open bio-medical corpora
- Host: GitHub
- URL: https://github.com/straymat/bio-medical_ner
- Owner: strayMat
- License: apache-2.0
- Created: 2018-07-04T16:05:45.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2019-03-21T08:49:43.000Z (over 7 years ago)
- Last Synced: 2025-04-11T00:34:35.708Z (about 1 year ago)
- Language: SQLPL
- Size: 17.6 MB
- Stars: 1
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Evaluation of YASET on various bio-medical datasets
This repo describes the code and the processes used to evaluate [Yaset](http://yaset.readthedocs.io/en/stable/), a neural model for NER on differents datasets. These experiences and their interpretations are precisely discribed in the following paper, [Tourille et al., 2018](http://www.aclweb.org/anthology/W18-5622).
## Corpora
The different corpora are:
+ [conll2003](https://github.com/strayMat/bio-medical_ner/tree/master/conll2003)
+ [medpost](https://github.com/strayMat/bio-medical_ner/tree/master/medpost)
+ [ncbi](https://github.com/strayMat/bio-medical_ner/tree/master/ncbi)
Each of the folder contains a README.md, commented jupyter notebooks, a data folder and partial summary of the results in a json directory.
## Utils
The auxilliary functions used in notebooks are discribed in [utils_paper](https://github.com/strayMat/bio-medical_ner/tree/master/utils_paper).
## Embeddings
The origin and construction of word embeddings used by the model are in [en_word_emb](https://github.com/strayMat/bio-medical_ner/tree/master/en_word_emb), a notebook describes how they are constructed.
## Requirements:
Install the Python dependencies with :
`pip install -r requirements.txt`
Install Yaset following [the instructions](http://yaset.readthedocs.io/en/stable/getting_started.html#installation)
## Citation
Tourille, Julien, Matthieu Doutreligne, Olivier Ferret, Aurélie Névéol, Nicolas Paris, et Xavier Tannier. « Evaluation of a Sequence Tagging Tool for Biomedical Texts ». Proceedings of the 9th International Workshop on Health Text Mining and Information Analysis (LOUHI 2018), 2018, pages 193–203.