基于原型网络的细粒度实体分类方法

细粒度实体分类任务作为命名实体识别任务的扩展,其目的是根据指称及其上下文,发掘实体更细粒度的类别含义。由于细粒度实体语料的标注代价较大,标注错误率较高,因此该文研究了在少量样本情况下的细粒度实体分类方法。该文首先提出了一种特征提取模型,能够分别从单词层面以及字符层面提取实体信息,随后结合原型网络将多标签分类任务转化为单标签分类任务,通过缩小空间中同类样本与原型的距离实现分类。该文使用少样本学习以及零样本学习两种设置在公开数据集FIGER(GOLD)上进行了实验,在少样本学习的设置下,较基线模型在三个指标中均有提升,其中macro-F₁的提升最大,为2.4%。

Fine-Grained Entity Typing with Prototypical Networks

As an extension of named entity recognition task, fine-grained entity typing task aims to assign more fine-grained types to entities according to mention and contexts. Due to the high cost and error-prone of the fine-grained types annotation, we study the fine-grained entity typing only by a small number of samples. This paper first proposes a feature extraction method which can extract entity information from word-level and character-level, respectively. Then, combining with prototype network, the method transforms the multi-class classification task into single-class classification task, and realizes fine-grained entity classification by calculating the distances from prototypes in metric space. Tested on the public dataset FIGER (GOLD) under the settings of the few-shot learning and the zero-shot learning, the proposed method achieves ideal results. Under the setting of the few-shot learning, the proposed method out-performs the baseline on all metrics, in particular the macro-F₁ is increased by 2.4%.