AMinerOpen is an open source community who focuses on developing and publishing elegant algorithms, models and tools for science big data mining and knowledge intelligence with AMiner resources.
This is not a code repo because most functions need large files which are not convenient for uploading. Therefore, we focus on providing APIs.
And this repo is on construction...
- Chinese and English pre-trained word embeddings based on 2 billion publication titles and abstracts
- Chinese and English pre-trained key word embeddings based on 2 billion publication key words
- Cross-lingual academic word (or key word) embeddings (Chinese-English)
- Their applications for keyword extraction, document clustering, etc.
- Text classifier of NSFC disciplines [repo]
- Hierarchical relation exploration [repo]
- Taxonomy extension by labeled documents [repo]
- Given a researcher's name and organization, extract structured information from web
If our APIs help you in some way, please consider cite the following publication(s):
- Jie Tang, Jing Zhang, Limin Yao, Juanzi Li, Li Zhang, and Zhong Su. ArnetMiner: Extraction and Mining of Academic Social Networks. In Proceedings of the Fourteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD’2008).