论文标题
基于BTPK的可解释方法，用于基于Talmudic公告逻辑的NER任务
BTPK-based interpretable method for NER tasks based on Talmudic Public Announcement Logic
论文作者
论文摘要
作为自然语言处理（NLP）的基本任务之一，命名实体识别（NER）是NLP下游任务的重要基本工具，例如信息提取，句法分析，机器翻译等。当前名称实体识别模型的内部操作逻辑对用户是黑框，因此用户没有依据来确定哪个名称实体更有意义。因此，对用户友好的解释识别过程对许多人来说非常有用。在本文中，我们提出了一种新颖的可解释方法BTPK（二进制talmudic公开公告逻辑模型），以帮助用户了解基于Talmudic公共公告逻辑的名称实体识别任务的内部识别逻辑。 BTPK模型还可以捕获输入句子中的语义信息，即句子的上下文依赖性。我们观察到BTPK的公开宣布介绍了BRNN的内部决策逻辑，从BTPK模型获得的解释向我们展示了BRNNS如何基本处理NER任务。
As one of the basic tasks in natural language processing (NLP), named entity recognition (NER) is an important basic tool for downstream tasks of NLP, such as information extraction, syntactic analysis, machine translation and so on. The internal operation logic of current name entity recognition model is black-box to the user, so the user has no basis to determine which name entity makes more sense. Therefore, a user-friendly explainable recognition process would be very useful for many people. In this paper, we propose a novel interpretable method, BTPK (Binary Talmudic Public Announcement Logic model), to help users understand the internal recognition logic of the name entity recognition tasks based on Talmudic Public Announcement Logic. BTPK model can also capture the semantic information in the input sentences, that is, the context dependency of the sentence. We observed the public announcement of BTPK presents the inner decision logic of BRNNs, and the explanations obtained from a BTPK model show us how BRNNs essentially handle NER tasks.
