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 1710.00969cs.CL
收藏

基于文本非线性表示的事件识别决策过程

Event Identification as a Decision Process with Non-linear Representation of Text

Tsinghua University(清华大学)

Yukun Yan, Daqi Zheng, Zhengdong Lu, Sen Song

摘要:

我们提出了无标度标识符网络(sfIN),一种新的模型,在文档中的事件识别。一般来说,sfIN首先将文档编码到多尺度内存堆栈中,然后通过执行多尺度动作来提取特殊事件,这可以被认为是一种特殊类型的序列标记。大规模动作的设计使其更有效地处理长文档。整个模型的训练与监督学习和强化学习。

英文摘要:

We propose scale-free Identifier Network(sfIN), a novel model for event identification in documents. In general, sfIN first encodes a document into multi-scale memory stacks, then extracts special events via conducting multi-scale actions, which can be considered as a special type of sequence labelling. The design of large scale actions makes it more efficient processing a long document. The whole model is trained with both supervised learning and reinforcement learning.

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。

↑