OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Services
This addresses the need for efficient, annotation-light models in academic knowledge services, though it is incremental as it builds on existing pre-training methods with domain-specific data.
The paper tackled the problem of building a unified backbone language model for academic knowledge services by pre-training OAG-BERT, which integrates heterogeneous entity knowledge and scientific corpora from the Open Academic Graph, and it has been deployed in real-world applications like reviewer recommendation for NSFC and paper tagging in AMiner.
Academic knowledge services have substantially facilitated the development of the science enterprise by providing a plenitude of efficient research tools. However, many applications highly depend on ad-hoc models and expensive human labeling to understand scientific contents, hindering deployments into real products. To build a unified backbone language model for different knowledge-intensive academic applications, we pre-train an academic language model OAG-BERT that integrates both the heterogeneous entity knowledge and scientific corpora in the Open Academic Graph (OAG) -- the largest public academic graph to date. In OAG-BERT, we develop strategies for pre-training text and entity data along with zero-shot inference techniques. In OAG-BERT, we develop strategies for pre-training text and entity data along with zero-shot inference techniques. Its zero-shot capability furthers the path to mitigate the need of expensive annotations. OAG-BERT has been deployed for real-world applications, such as the reviewer recommendation function for National Nature Science Foundation of China (NSFC) -- one of the largest funding agencies in China -- and paper tagging in AMiner. All codes and pre-trained models are available via the CogDL toolkit.