摘要
生成式阅读理解是机器阅读理解领域一项新颖且极具挑战性的研究。与主流的抽取式阅读理解相比,生成式阅读理解模型不再局限于从段落中抽取答案,而是能结合问题和段落生成自然和完整的表述作为答案。然而,现有的生成式阅读理解模型缺乏对答案在段落中的边界信息以及对问题类型信息的理解。为解决上述问题,该文提出一种基于多任务学习的生成式阅读理解模型。该模型在训练阶段将答案生成任务作为主任务,答案抽取和问题分类任务作为辅助任务进行多任务学习,同时学习和优化模型编码层参数;在测试阶段加载模型编码层进行解码生成答案。实验结果表明,答案抽取模型和问题分类模型能够有效提升生成式阅读理解模型的性能。
Generative reading comprehension is a novel and challenging issue in machine reading comprehension.Compared with the mainstream extractive reading comprehension,generative reading comprehension model is aimed for combining questions and paragraphs to generate natural and complete statements as answers.To understand of the boundary information of answers in paragraphs and the question type information,this paper proposes a generative reading comprehension model based on multi-task learning.In the training phase,the model takes the answer generation as the main task,and the answer extraction and question classification tasks as auxiliary tasks for multi-task learning.The model simultaneously learns and optimizes the parameters of the encoding layer,then it loads the encoding layer in the test phase to decode and generate the answers.The experimental results show that the answer extraction model and the question classification model can effectively improve the performance of the generative reading comprehension model.
作者
钱锦
黄荣涛
邹博伟
洪宇
QIAN Jin;HUANG Rongtao;ZOU Bowei;HONG Yu(School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China;Institute for Infocomm Research,138632,Singapore)
出处
《中文信息学报》
CSCD
北大核心
2021年第12期103-111,121,共10页
Journal of Chinese Information Processing
基金
国家自然科学基金(61703293,61672368,61672367)
江苏省高校优势学科建设工程资助项目
关键词
多任务学习
生成式阅读理解
multi-task learning
generative reading comprehension
