基于全局覆盖机制与表示学习的生成式知识问答技术  

Generative Knowledge Question Answering Technology Based on Global Coverage Mechanism and Representation Learning

作　　者：刘琼昕 王亚男[2] 龙航 王佳升 卢士帅 LIU Qiong-Xin;WANG Ya-Nan;LONG Hang;WANG Jia-Sheng;LU Shi-Shuai(Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications,Beijing 100081;School of Computer Science and Technology,Beijing Institute of Technology,Beijing 100081)

机构地区：[1]北京市海量语言信息处理与云计算应用工程技术研究中心,北京100081 [2]北京理工大学计算机学院,北京100081

出　　处：《自动化学报》2022年第10期2392-2405,共14页Acta Automatica Sinica

基　　金：国家自然科学基金(62072039)资助。

摘　　要：针对现有生成式问答模型中陌生词汇导致答案准确率低下的问题和模式混乱导致的词汇重复问题,本文提出引入知识表示学习结果的方法提高模型识别陌生词汇的能力,提高模型准确率.同时本文提出使用全局覆盖机制以平衡不同模式答案生成的概率,减少由预测模式混乱导致的重复输出问题,提高答案的质量.本文在知识问答模型基础上结合知识表示学习的推理结果,使模型具备模糊回答的能力.在合成数据集和现实世界数据集上的实验证明了本模型能够有效地提高生成答案的质量,能对推理知识进行模糊回答.Aiming at the problem of low answer accuracy caused by unfamiliar words in the existing generative question answering model and the problem of vocabulary repetition caused by pattern confusion, this paper proposes a method of introducing knowledge representation learning results to improve the model’s ability to recognize unfamiliar words and improve the accuracy of the model. At the same time, this paper proposes to use a global coverage mechanism to balance the probability of answer generation in different modes, reduce the repeated output problem caused by the confusion of prediction modes, and improve the quality of the answer. Based on the knowledge question answering model, this paper combines the inference results of knowledge representation learning,so that the model has the ability to answer fuzzy answers. Experiments on synthetic datasets and real-world datasets demonstrate that this model can effectively improve the quality of generated answers and can provide fuzzy answers to reasoning knowledge.

关 键 词：生成式知识问答 覆盖机制 知识表示学习 自然语言处理 深度学习 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]