Syntax-guided text generation via graph neural network  

作　　者：Qipeng GUO Xipeng QIU Xiangyang XUE Zheng ZHANG 

机构地区：[1]Shanghai Key Laboratory of Intelligent Information Processing,School of Computer Science,Fudan University,Shanghai 200433,China [2]NYU Shanghai and AWS Shanghai AI Lab,Shanghai 200335,China

出　　处：《Science China(Information Sciences)》2021年第5期63-72,共10页中国科学（信息科学）（英文版）

基　　金：supported by National Key Research and Development Program of China(Grant No.2018YFC0831103);Shanghai Municipal Science and Technology Major Project(Grant No.2018SHZDZX01);Zhejiang Lab。

摘　　要：Text generation is a fundamental and important task in natural language processing.Most of the existing models generate text in a sequential manner and have difficulty modeling complex dependency structures.In this paper,we treat the text generation task as a graph generation problem exploiting both syntactic and word-ordering relationships.Leveraging the framework of the graph neural network,we propose the word graph model.During the process,the model builds a sentence incrementally and maintains syntactic integrity via a syntax-driven,top-down,breadth-first generation process.Experimental results on both synthetic and real text generation tasks show the efficacy of our approach.

关 键 词：text generation deep learning graph neural network dependency parsing 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.1[自动化与计算机技术—控制科学与工程]