论文标题
关于发现跨度的实证研究
An Empirical Study on Finding Spans
论文作者
论文摘要
我们介绍了一项有关跨度查找方法的实证研究，在文本中选择连续令牌以进行某些下游任务。我们专注于可以在培训端到端信息提取系统中采用的方法，并发现没有考虑任务属性的情况下没有确定的解决方案，并提供了我们的观察以帮助未来的设计选择：1）标记方法通常会产生更高的精度，而跨度枚举和边界预测会提供更高的回忆； 2）跨度类型信息可以使边界预测方法受益； 3）在大多数情况下，其他上下文化无助于跨度查找。
We present an empirical study on methods for span finding, the selection of consecutive tokens in text for some downstream tasks. We focus on approaches that can be employed in training end-to-end information extraction systems, and find there is no definitive solution without considering task properties, and provide our observations to help with future design choices: 1) a tagging approach often yields higher precision while span enumeration and boundary prediction provide higher recall; 2) span type information can benefit a boundary prediction approach; 3) additional contextualization does not help span finding in most cases.
