基于深度层次特征的阅读理解模型  

Machine Comprehension Model on Deep Hierarchical Features

作　　者：霍欢[1,2] 王忠萌 HUO Huan;WANG Zhongmeng(School of Optical-Electrical and Computer Engineering,Shanghai University of Science and Technology,Shanghai 200093,China;Shanghai Key Laboratory of Data Science,Fudan University,Shanghai 201203,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093 [2]复旦大学上海市数据科学重点实验室,上海201203

出　　处：《中文信息学报》2018年第12期132-142,共11页Journal of Chinese Information Processing

基　　金：国家自然科学基金(61003031);上海重点科技攻关项目(14511107902);上海市工程中心建设项目(GCZX14014);上海市一流学科建设项目(XTKX2012);上海市数据科学重点实验室开放课题资助课题(201609060003);沪江基金研究基地专项(C14001).

摘　　要：对于面向真实场景的中文机器阅读,理解文本所呈现的复杂信息至关重要。针对多篇章的连续答案片段型中文机器阅读任务,该文提出一种基于深度层次特征的模型,来提取细节、片段、全文三个层次的深度特征,从而多角度把握篇章包含的信息。在该模型中,词语经过词向量表示后,经过循环(recurrent)层编码后得到细节特征,并经过若干卷积(convolution)层和高速公路(highway)层等构造片段特征,同时对候选篇章进行全文特征的提取来进行整体的考察。最后,通过这些特征来确定答案所在篇章以及该篇章内的答案片段所在位置。在2018机器阅读理解技术竞赛中,单模型取得57.55的Rouge-L分数和50.87的Bleu-4分数,实验取得较好效果。For Chinese machine reading tasks of multi-passage continuous answer spans,this paper proposes a model based on deep hierarchical features to extract the three-level deep features in details,in snippets,and in full-texts.In this model,words represented by word vectors are encoded in a recurrent layer to obtain the detailed features.The snippets features are constructed through several convolution layers and highway layers.And the full-text features are extracted from candidate passages to perform the overall inspection.Finally,through these features,the passage where the answer is located and the answer spans within the passage is determined.Experimented on 2018 NLP Challenge on Machine Reading Comprehension,the proposed model achieves a Rouge-L score of 57.55 and a Bleu-4 score of 50.87.

关 键 词：机器阅读 层次特征 卷积 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]