We study the problem of few-shot Fine-grained Entity Typing (FET), where only a few annotated entity mentions with contexts are given for each entity type. Recently, prompt-based tuning has demonstrated superior performance to standard fine-tuning in few-shot scenarios by formulating the entity type classification task as a ''fill-in-the-blank'' problem. This allows effective utilization of the strong language modeling capability of Pre-trained Language Models (PLMs). Despite the success of current prompt-based tuning approaches, two major challenges remain: (1) the verbalizer in prompts is either manually designed or constructed from external knowledge bases, without considering the target corpus and label hierarchy information, and (2) current approaches mainly utilize the representation power of PLMs, but have not explored their generation power acquired through extensive general-domain pre-training. In this work, we propose a novel framework for few-shot FET consisting of two modules: (1) an entity type label interpretation module automatically learns to relate type labels to the vocabulary by jointly leveraging few-shot instances and the label hierarchy, and (2) a type-based contextualized instance generator produces new instances based on given instances to enlarge the training set for better generalization. On three benchmark datasets, our model outperforms existing methods by significant margins. Code can be found at https://github.com/teapot123/Fine-Grained-Entity-Typing.
翻译:我们研究了少见的精美实体打字(FET)问题,目前只有几个附加注释的实体提到每个实体类型的背景。最近,快速的调试显示,在几个发件情况下,通过将实体类型分类任务设计成“填充空白”问题,在几个发件情况下,其性能优于标准微调。这允许有效利用培训前语言模型(PLMs)强大的语言模型(PLMs)能力。尽管当前快速调试方法取得了成功,但仍存在两大挑战:(1) 快速调试的调音器要么是用外部知识基础手工设计,要么是用外部知识基础构建的,而没有考虑目标内容和标签等级信息;(2) 目前的方法主要是利用PLMS的代表能力,但没有探索通过广泛的通用前培训获得的生成能力。在这项工作中,我们为少数发件FET提供了一个新的框架,由两个模块组成:(1) 实体类型标签解释模块自动学习将类型标签与词汇联系起来,方法是联合利用少数发件实例和标签等级,以及(2) 类型化背景化的图像生成器,主要利用PLMMS/F的模型,在现有的标准模型上产生新的实例。在现有的标准上,可以扩大现有的标准。