https://github.com/gatenlp/gateplugin-oscar4

GATE PR that uses OSCAR4 to annotate chemical named entities.
https://github.com/gatenlp/gateplugin-oscar4

Last synced: about 2 months ago
JSON representation

GATE PR that uses OSCAR4 to annotate chemical named entities.

• Host: GitHub
• URL: https://github.com/gatenlp/gateplugin-oscar4
• Owner: GateNLP
• License: other
• Created: 2021-11-04T12:58:06.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2023-02-10T13:48:57.000Z (almost 2 years ago)
• Last Synced: 2024-04-16T07:59:26.038Z (9 months ago)
• Language: Java
• Homepage:
• Size: 47.9 KB
• Stars: 0
• Watchers: 12
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# Chemical Named Entity Recognizer

GATE PR that uses [OSCAR4](https://github.com/BlueObelisk/oscar4) to annotate documents

More details on OSCAR4, including a number of example texts, can be found in [this publication](http://dx.doi.org/10.1186/1758-2946-3-41). One simple example, from that paper would be _"The quick brown ethyl acetate jumps over the lazy bromine"_ which results in two annotations over _ethyl acetate_ and _bromine_.

The tagger produces annotations of a single type, namely `ChemicalNE`. These annotations have the following features:

- *type:* the type of NE. Usually `compound`

- *Std_InChI:* The standard [International Chemical Identifier](https://en.wikipedia.org/wiki/International_Chemical_Identifier) for the recognised NE.

- *Std_InChiKey:* A hashed version of the Std_InChi key useful for web searches etc.

- *SMILES:* The named entity described using the [simplified molecular-input line-entry system (SMILES)](https://en.wikipedia.org/wiki/Simplified_molecular-input_line-entry_system)