一种基于参考规范的专业文本生成方法

Profession Oriented Text Generation Based on Reference Specifications

参考规范是指专业知识点的相关文本描述,参考规范指导下的文本生成任务要求自动生成的文本满足与参考规范的语义相关性和知识点匹配性,是自然语言处理领域中的困难问题。相关工作主要控制生成文本的情感、态度等通用性质,无法满足专业层面的复杂控制需求。为此,该文提出了基于对抗架构的专业文本生成模型(PT-GAN),采用多个独立的生成器分别生成不同知识点匹配程度的文本,各生成器均为自编码器结构,其中编码器用于提取参考规范文本的知识点语义特征,解码器用于生成文本;采用两个判别器同时对生成文本的语言规范和专业知识进行指导,其中连贯性判别器用于指导语言规范,专业性判别器用于控制专业层面属性。在多个国家级专业考试真实数据集上进行实验,结果显示该文模型在语言连贯性、与参考规范的语义相关性和知识点匹配性上均有明显提升,更符合该场景下的文本生成需求。

Reference specifications refer to the text description of professional knowledge points,which are used to guide the text generation.In this paper,we propose a profession oriented text generation model based on adversarial architecture(PT-GAN),using several independent generators for the texts on different matching degrees of knowledge points.Each generator is an auto-encoder,where the encoder is used to extract the features of reference specifications,and the decoder is used to generate text.We use two discriminators to guide the text generation on both the linguistic norms and professional knowledge.The linguistic discriminator guides the coherence and the profession discriminator is used to control professional attributes.Experiments on national profession qualification examination datasets show that the proposed model has a significant improvement comparing with other methods on coherence,relevance with reference specifications,and on matching knowledge points.