Overview
This is a page for our KDD'20 manuscript: A framework for constructing a huge name disambiguation dataset: algorithms, visualization and human collaboration.
Experiment Code
The implmentation of proposed name disambiguation model is available at https://github.com/timxiao317/E2E-Name-Disambiguation
Annotation System Demo
The demo system is available at http://39.98.182.236:8000/toolscomparepubs
We provide several ambiguous author names for demo users to disambiguate:
- Ge_Yu
- Atsushi_Ikeda
Wei_Wen
Please paste one of them into the input box and have a try :).
The introduction of the system is available in the appendix of our manuscript.
If you have any problems concerning the demo system, please feel free to contact us through this email joeyxiao317@gmail.com
Dataset
Framework
In order to build such a large manually-labeled dataset, we proposed a novel annotation framework where the human and computers collaborate efficiently and precisely.
More technical details are available at
https://drive.google.com/file/d/1te4i8K2QbqrV0Wx8Je8FnX3uidmKITTE/view