arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.00916cs.CLcs.AI
收藏

如何训练你的代理阅读和写作

How to Train Your Agent to Read and Write

School of Software Engineering, South China University of Technology(华南理工大学软件学院);Pazhou Laboratory(琶洲实验室);University of Adelaide(阿德莱德大学);Key Laboratory of Big Data and Intelligent Robot, Ministry of Education(大数据与智能机器人教育部重点实验室)

Li Liu, Mengge He, Guanghui Xu, Mingkui Tan, Qi Wu

摘要:

阅读和撰写研究论文是一个合格的研究人员应该掌握的最特权的能力之一。但是,新的研究人员(\eg{students})很难完全{掌握}这种能力。如果我们能训练一个智能代理来帮助人们阅读和总结论文,甚至可能发现和利用潜在的知识线索来撰写新颖的论文,那将是非常迷人的。虽然已经存在专注于总结(\emph{i.e.},阅读)给定文本中的知识或基于给定知识生成(\emph{i.e.},书写)文本的现有工作,但是同时阅读和书写的能力仍处于开发中。通常,这需要智能体从给定的文本材料中充分理解知识,并生成正确和流畅的小说段落,这在实践中非常具有挑战性。在本文中,我们提出了一个深度读者-作家(DRAW)网络,它由一个\textit{Reader},可以从输入段落中提取知识图谱(KG),发现潜在的知识,一个图形到文本的\textit{Writer},生成一个新的段落,和一个\textit{Reviewer},从三个不同的方面审查所生成的段落。大量的实验表明,我们的DRAW网络在AGENDA和M-AGENDA数据集上的性能优于考虑的基线和几种最先进的方法。我们的代码和补充文件在https://github.com/menggehe/DRAW上发布。

英文摘要:

Reading and writing research papers is one of the most privileged abilities that a qualified researcher should master. However, it is difficult for new researchers (\eg{students}) to fully {grasp} this ability. It would be fascinating if we could train an intelligent agent to help people read and summarize papers, and perhaps even discover and exploit the potential knowledge clues to write novel papers. Although there have been existing works focusing on summarizing (\emph{i.e.}, reading) the knowledge in a given text or generating (\emph{i.e.}, writing) a text based on the given knowledge, the ability of simultaneously reading and writing is still under development. Typically, this requires an agent to fully understand the knowledge from the given text materials and generate correct and fluent novel paragraphs, which is very challenging in practice. In this paper, we propose a Deep ReAder-Writer (DRAW) network, which consists of a \textit{Reader} that can extract knowledge graphs (KGs) from input paragraphs and discover potential knowledge, a graph-to-text \textit{Writer} that generates a novel paragraph, and a \textit{Reviewer} that reviews the generated paragraph from three different aspects. Extensive experiments show that our DRAW network outperforms considered baselines and several state-of-the-art methods on AGENDA and M-AGENDA datasets. Our code and supplementary are released at https://github.com/menggehe/DRAW.

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。

↑