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 1809.03449cs.AIcs.CL
收藏

一般知识在机器阅读理解中的显式利用

Explicit Utilization of General Knowledge in Machine Reading Comprehension

York University(约克大学)

Chao Wang, Hui Jiang

摘要:

为了弥补机器阅读理解(MRC)模型与人类之间的差距,主要体现在对数据的渴求和对噪声的鲁棒性上,本文探讨如何将MRC模型的神经网络与人类的一般知识相结合。一方面,我们提出了一种数据丰富的方法,它使用WordNet提取词间语义连接作为一般知识,从每个给定的问题对。另一方面,我们提出了一个端到端的MRC模型命名为知识辅助阅读器(KAR),它显式地使用上述提取的一般知识,以协助其注意力机制。基于数据富集方法,KAR在性能上与最先进的MRC模型相当,并且对噪声的鲁棒性明显优于它们。当只有一个子集(20%-80%)的训练样本是可用的,KAR优于国家的最先进的MRC模型的大幅度,仍然是合理的噪音鲁棒性。

英文摘要:

To bridge the gap between Machine Reading Comprehension (MRC) models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, in this paper, we explore how to integrate the neural networks of MRC models with the general knowledge of human beings. On the one hand, we propose a data enrichment method, which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair. On the other hand, we propose an end-to-end MRC model named as Knowledge Aided Reader (KAR), which explicitly uses the above extracted general knowledge to assist its attention mechanisms. Based on the data enrichment method, KAR is comparable in performance with the state-of-the-art MRC models, and significantly more robust to noise than them. When only a subset (20%-80%) of the training examples are available, KAR outperforms the state-of-the-art MRC models by a large margin, and is still reasonably robust to noise.

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。

↑