基于预训练语义编码的判断句答案推理  

Judgment Answer Inference Bsaed on Pre-trained Semantic Encoding

作　　者：李飞 王颜颜 王超 黄友志 LI Fei;WANG Yanyan;WANG Chao;HUANG Youzhi(School of Computer Science and Technology,University of Science and Technology of China,Hefei 230026,China;Guochuang Cloud Technology Ltd,Hefei 230088,China)

机构地区：[1]中国科学技术大学计算机科学与技术学院,安徽合肥230026 [2]科大国创云网科技有限公司,安徽合肥230088

出　　处：《软件导刊》2024年第1期75-80,共6页Software Guide

摘　　要：目前大规模文本问答依赖句子表征从候选文本中检索答案,但是忽略了有些答案需要进一步推理,无法直接从文中获取,比如判断句。为解决此类问题,一个面向大规模文本的判断句答案生成方法被提出。首先在语义编码器中通过对大规模文本进行预训练获取语义编码器,对问题、依据进行语义编码;其次在答案生成器中基于对比学习构造正负样本进行数据增强;之后在答案依据获取器中通过使用Faiss实现问题和大规模文本的快速表征与匹配。在最终的判断句问答中,准确率高达96.58%,验证了该方法的有效性。Currently,large-scale text question answering relies on sentence representation to retrieve answers from candidate texts,but it ig-nores that some answers require further reasoning and cannot be obtained directly from the text,such as judgment sentences.To solve such problems,a judgment sentence answer generation method for large-scale text is proposed.Firstly,in the semantic encoder,the semantic en-coder is obtained by continuing to pre-train large-scale texts,and the questions and cues are semantically encoded.Sceondly,in the answer generator module,positive and negative samples are constructed based on contrastive learning for data enhancement.Then fast characteriza-tion and matching of questions and large-scale text is achieved by using Faiss in the answer basis obtainer.The accuracy of the final judgment sentence question and answer is as high as 96.58%,which verifies the effectiveness of this method.

关 键 词：智能问答 开放域问答 问答分类器 语义编码 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]