Recent years have seen the paradigm shift of Named Entity Recognition (NER)
systems from sequence labeling to span prediction. Despite its preliminary
effectiveness, the span prediction model's architectural bias has not been
fully understood. In this paper, we first investigate the strengths and
weaknesses when the span prediction model is used for named entity recognition
compared with the sequence labeling framework and how to further improve it,
which motivates us to make complementary advantages of systems based on
different paradigms. We then reveal that span prediction, simultaneously, can
serve as a system combiner to re-recognize named entities from different
systems' outputs. We experimentally implement 154 systems on 11 datasets,
covering three languages, comprehensive results show the effectiveness of span
prediction models that both serve as base NER systems and system combiners. We
make all code and datasets available: \url{this https URL},
as well as an online system demo: \url{this http URL}. Our model also has
been deployed into the ExplainaBoard platform, which allows users to flexibly
perform a system combination of top-scoring systems in an interactive way:
\url{this http URL}.

本文研究了使用 span prediction 和 sequence labeling 框架进行命名实体识别的优缺点，并提出了系统组合的方法来重新识别来自不同系统的命名实体，并在 11 个数据集上进行了 154 个系统的实验，证明了 span prediction 也可以作为基础 NER 系统和系统组合器，同时也将我们的模型部署到 ExplainaBoard 平台上。