Named Entity Recognition (NER) is a low-level task often used as a foundation for solving higher level NLP problems. In the context of character detection in novels, NER false negatives can be an issue as they possibly imply missing certain characters or relationships completely. In this article, we demonstrate that applying a straightforward data augmentation technique allows training a model achieving higher recall, at the cost of a certain amount of precision regarding ambiguous entities. We show that this decrease in precision can be mitigated by giving the model more local context, which resolves some of the ambiguities.

翻译：命名实体识别（NER）是一项低级任务，常被用作解决更高级自然语言处理问题的基础。在小说角色检测的语境中，NER的假阴性可能成为问题，因为它们可能导致完全遗漏某些角色或关系。本文证明，应用一种直接的数据增强技术，可以训练出实现更高召回率的模型，但代价是对于歧义实体的精确度会有所降低。我们表明，这种精确度的下降可以通过向模型提供更多局部上下文来缓解，这能解决一部分歧义问题。