机器阅读理解中观点型问题的求解策略研究

A Study on Solution Strategy of Opinion-Problems in Machine Reading Comprehension

针对机器阅读理解中观点型问题的求解,提出一个端到端深度学习模型,使用Bi-GRU对文章和问题进行上下文语义编码,然后运用基于拼接、双线性、点乘和差集4种函数的注意力加上Query2Context和Context2Query两个方向注意力的融合算法获取文章和问题的综合语义信息,之后运用多层注意力转移推理机制不断聚焦,进一步获取更加准确的综合语义,最终将其与候选答案进行比较,选出正确答案。该模型在AIchallager2018观点型阅读理解中文测试数据集上准确率达到76.79%,性能超过基线系统。此外,该文尝试文章以句子序列作为输入表示进行答案求解,准确率达到78.48%,获得较好试验效果。

In order to solve the opinion-problems of machine reading comprehension,an end-to-end deep learning model is proposed.In this paper,Bi-GRU is used to contextually encode passages and problems.And then four kinds of attentions,including the concatenated attention,the bilinear attention,the element-wise dot attention and minus attention,are applied with the fusion of Query2 Context and Context2 Query attentions to obtain the comprehensive semantic information of the passage and the problem.This model further employs the multi-level attention transfer reasoning mechanism to obtain more accurate comprehensive semantics.The accuracy reaches 76.79%on the AIchallager 2018 opinion reading comprehension Chinese test data set.In addition,using the sentence sequence as input,the method could be boosted to an accuracy of 78.48%.