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 1906.09320cs.CL
收藏

基于递归随机游走网络学习的神经元集合实体连接

Neural Collective Entity Linking Based on Recurrent Random Walk Network Learning

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);Xiamen University(厦门大学);Rochester University(罗切斯特大学);Xiaomi AI Lab, Xiaomi Inc.(小米公司小米人工智能实验室)

Mengge Xue, Weiming Cai, Jinsong Su, Linfeng Song, Yubin Ge, Yubao Liu, Bin Wang

摘要:

得益于神经网络在学习语义表示方面的优异能力,现有的实体链接研究都采用神经网络来利用实体链接决策之间的局部相容性和全局依赖性来消除目标实体的歧义。然而,大多数神经集体EL方法完全依赖于神经网络来自动建模不同EL决策之间的语义依赖关系,缺乏外部知识的指导。在本文中,我们提出了一种新的端到端的神经网络与经常性的随机游走层集体EL,它引入外部知识来模拟不同EL决策之间的语义相互依赖性。具体来说,我们首先建立一个模型的基础上,局部上下文功能,然后堆栈随机游走层,以加强相关EL决策的证据,高概率的决策,其中候选实体之间的语义相互依赖性主要是从外部知识库诱导。最后,一个语义正则化,保持集体EL决策的一致性被纳入到传统的目标函数,使外部知识库可以充分利用集体EL决策。在不同数据集上的实验结果和深入分析表明,我们的模型比其他最先进的模型具有更好的性能。我们的代码和数据在\url{https://github.com/DeepLearnXMU/RRWEL}上发布。

英文摘要:

Benefiting from the excellent ability of neural networks on learning semantic representations, existing studies for entity linking (EL) have resorted to neural networks to exploit both the local mention-to-entity compatibility and the global interdependence between different EL decisions for target entity disambiguation. However, most neural collective EL methods depend entirely upon neural networks to automatically model the semantic dependencies between different EL decisions, which lack of the guidance from external knowledge. In this paper, we propose a novel end-to-end neural network with recurrent random-walk layers for collective EL, which introduces external knowledge to model the semantic interdependence between different EL decisions. Specifically, we first establish a model based on local context features, and then stack random-walk layers to reinforce the evidence for related EL decisions into high-probability decisions, where the semantic interdependence between candidate entities is mainly induced from an external knowledge base. Finally, a semantic regularizer that preserves the collective EL decisions consistency is incorporated into the conventional objective function, so that the external knowledge base can be fully exploited in collective EL decisions. Experimental results and in-depth analysis on various datasets show that our model achieves better performance than other state-of-the-art models. Our code and data are released at \url{https://github.com/DeepLearnXMU/RRWEL}.

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。

↑