We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document. Unlike previous models, we do not collapse the query into a single vector, instead we deploy an iterative alternating attention mechanism that allows a fine-grained exploration of both the query and the document. Our model outperforms state-of-the-art baselines in standard machine comprehension benchmarks such as CNN news articles and the Children's Book Test (CBT) dataset.
ART: The Alternating Reading Task Corpus for Speech Entrainment and Imitation
Italian Institute of Technology(意大利技术研究院);University of Ferrara(费拉拉大学);Constantine the Philosopher University in Nitra(尼特拉君士坦丁哲学家大学);Institute of Informatics, SAS(斯洛伐克科学院信息学研究所);Aix Marseille University(艾克斯-马赛大学)
Document-Level Event Extraction via Human-Like Reading Process
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Beijing University of Posts and Telecommunications(北京邮电大学)
文档级事件提取(DEE)特别棘手,因为它带来了两个挑战:分散参数和多事件。第一个挑战意味着一个事件记录的参数可以驻留在文档中的不同句子中,而第二个挑战反映了一个文档可以同时包含多个这样的事件记录。本文从人类阅读认知的角度出发,提出了一种基于文本事件的人类阅读启发提取器(Human Reading inspired Extractor for Document Events,HRE),该方法将文本事件分解为粗读和精读两个迭代阶段。具体而言,第一阶段浏览文档以检测事件的发生,第二阶段用于提取特定的事件参数。对于每一个具体的事件角色,精细阅读从句子到字符分层工作,以确定跨句子的论点,从而解决分散的论点问题。同时,通过多轮的粗读探索,发现未检测到的事件,从而解决了多事件问题。实验结果表明,HRE优于以往的竞争方法。
A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
Graduate School of Artificial Intelligence, POSTECH, Republic of Korea(韩国POSTECH人工智能研究生院);Department of Computer Science and Engineering, POSTECH, Republic of Korea(韩国POSTECH计算机科学与工程系)
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);New York University Abu Dhabi(纽约大学阿布扎比分校);IBM Research AI(IBM研究院人工智能部门);Qassim University(卡西姆大学)