摘要
该文描述了ZWYC团队在"2018机器阅读理解技术竞赛"上提出的机器理解模型。所提出模型将机器阅读理解问题建模成连续文本片段抽取问题,提出基于富语义特征的神经交互网络模型。为了充分使用答案标注信息,模型首先对数据进行细致的重构,让人工标注的多个答案信息都能融合到数据中。通过特征工程,对每个词构建富语义表征。同时提出一种简单有效的问题和文档交互的方式,得到问题感知的文档表征。基于多个文档串接的全局表征,模型进行答案文本预测。在最终测试集上,该模型获得了目前先进的结果,在105支队伍中排名第2。
This paper describes the model proposed in"2018 NLP Challenge on Machine Reading Comprehension"by ZWYC team.Treated the machine reading comprehension as extracting the text span from the documents,this paper proposes a feature-rich neural interaction network.In order to effectively use the information of golden answers,our model first reconstructs the data in detail so that all golden answer information can be integrated.Then a feature-rich semantic representation is built for each word.Moreover,a simple but effective network is designed for question-aware representation for each document by captuing the interaction between questions and documents.The proposed model predicts answer text based on global representations of multiple candidate documents,leading to the runner-up position among 105 teams.
作者
尹伊淳
张铭
YIN Yichun;ZHANG Ming(School of Electronics Engineering and Computer Science,Peking University,Beijing 100871,China)
出处
《中文信息学报》
CSCD
北大核心
2018年第11期112-116,共5页
Journal of Chinese Information Processing
基金
国家自然科学基金(61472006
61772039)
国家自然科学基金(91646202)
北京市科技计划新一代人工智能技术培育项目(Z181100008918005)
关键词
机器阅读理解
数据重构
神经网络
machine reading comprehension
data reconstruction
neural network