arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.08853cs.LGcs.AIcs.CLcs.NE
收藏

面向对象神经程序设计(OONP)在文档理解中的应用

Object-oriented Neural Programming (OONP) for Document Understanding

Tsinghua University(清华大学);Beijing Innovation Center for Future Chip, Tsinghua University(清华大学北京未来芯片创新中心)

Zhengdong Lu, Xianggen Liu, Haotian Cui, Yukun Yan, Daqi Zheng

摘要:

我们提出了面向对象的神经编程(OONP),在特定领域的语义解析文件的框架。基本上,OONP读取文档并将其解析为预先设计的面向对象的数据结构(本文中称为本体),该数据结构反映文档的特定于领域的语义。OONP解析器将语义解析建模为决策过程:基于神经网络的阅读器依次遍历文档,在此过程中,它构建并更新中间本体,以总结其对所涵盖文本的部分理解。OONP支持一系列丰富的操作(包括符号和可微分)来组成本体,以及各种各样的形式(包括符号和可微分)来表示状态和文档。OONP解析器可以用不同形式和强度的监督来训练,包括监督学习(SL)、强化学习(RL)以及两者的混合。我们对合成和真实世界的文档解析任务的实验表明,OONP可以学习处理相当复杂的本体与训练数据的适度大小。

英文摘要:

We propose Object-oriented Neural Programming (OONP), a framework for semantically parsing documents in specific domains. Basically, OONP reads a document and parses it into a predesigned object-oriented data structure (referred to as ontology in this paper) that reflects the domain-specific semantics of the document. An OONP parser models semantic parsing as a decision process: a neural net-based Reader sequentially goes through the document, and during the process it builds and updates an intermediate ontology to summarize its partial understanding of the text it covers. OONP supports a rich family of operations (both symbolic and differentiable) for composing the ontology, and a big variety of forms (both symbolic and differentiable) for representing the state and the document. An OONP parser can be trained with supervision of different forms and strength, including supervised learning (SL) , reinforcement learning (RL) and hybrid of the two. Our experiments on both synthetic and real-world document parsing tasks have shown that OONP can learn to handle fairly complicated ontology with training data of modest sizes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑