HOSMEL: A Hot-Swappable Modularized Entity Linking Toolkit for Chinese

We investigate the usage of entity linking (EL) in downstream tasks and present the first modularized EL toolkit for easy task adaptation. Different from the existing EL methods that deal with all the features simultaneously, we modularize the whole model into separate parts with each feature. This decoupled design enables flexibly adding new features without retraining the whole model as well as flow visualization with better interpretability of the EL result. We release the corresponding toolkit, HOSMEL, for Chinese, with three flexible usage modes(1), a live demo(2), and a demonstration video(3). Experiments on two benchmarks for the question answering task demonstrate that HOSMEL achieves much less time and space consumption as well as significantly better accuracy performance compared with existing SOTA EL methods. We hope the release of HOSMEL will call for more attention to study EL for downstream tasks in non-English languages.