arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.07211cs.IRcs.CL
收藏

面向基于知识的IR的深度神经方法

Toward a Deep Neural Approach for Knowledge-Based IR

IRIT, Université de Toulouse(图卢兹大学信息与电信研究所);Sorbonne Universités, UPMC Univ Paris 06(索邦大学,巴黎第六大学(皮埃尔和玛丽·居里大学));CNRS, LIP6 UMR 7606(法国国家科学研究中心,LIP6信息与系统科学实验室)

Gia-Hung Nguyen, Lynda Tamine, Laure Soulier, Nathalie Bricon-Souf

摘要:

本文处理的问题之间的语义差距的文件和一个特定的信息检索任务中的查询。在这种情况下,知识库(KBs)已经被认为是有价值的手段,因为它们允许实体之间的显式关系的表示。然而,它们并不一定代表可能隐藏在语料库中的隐含关系。后一个问题是解决最近的作品处理深表征学习的文本。考虑到这一点,我们认为,在支持文档查询匹配的深度神经架构中嵌入知识库将产生单词及其语义关系的细粒度潜在表示。在本文中,我们回顾了基于神经的文档排序的主要方法,以及那些通过知识库的实体和关系的潜在表示方法。然后,我们提出了一些将知识库纳入深度神经方法进行文档排序的方法。更具体地说,本文主张知识库可以用来支持增强的潜在表示的查询和文档的基础上的分布式和关系语义或作为一个语义翻译器之间的潜在的分布式表示。

英文摘要:

This paper tackles the problem of the semantic gap between a document and a query within an ad-hoc information retrieval task. In this context, knowledge bases (KBs) have already been acknowledged as valuable means since they allow the representation of explicit relations between entities. However, they do not necessarily represent implicit relations that could be hidden in a corpora. This latter issue is tackled by recent works dealing with deep representation learn ing of texts. With this in mind, we argue that embedding KBs within deep neural architectures supporting documentquery matching would give rise to fine-grained latent representations of both words and their semantic relations. In this paper, we review the main approaches of neural-based document ranking as well as those approaches for latent representation of entities and relations via KBs. We then propose some avenues to incorporate KBs in deep neural approaches for document ranking. More particularly, this paper advocates that KBs can be used either to support enhanced latent representations of queries and documents based on both distributional and relational semantics or to serve as a semantic translator between their latent distributional representations.

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。

↑