Semantically Enhanced Models for Commonsense Knowledge Acquisition

被引：6

作者：

Alhussien, Ikhlas ^{[1
]}

Cambria, Erik ^{[1
]}

Zhang NengSheng ^{[2
]}

机构：

[1] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore

[2] Agcy Sci Technol & Res, Singapore Inst Mfg Technol, Singapore, Singapore

来源：

2018 18TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW) | 2018年

关键词：

Knowledge graph embeddings; Commonsense; LARGE-SCALE;

D O I：

10.1109/ICDMW.2018.00146

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Commonsense knowledge is paramount to enable intelligent systems. Typically, it is characterized as being implicit and ambiguous, hindering thereby the automation of its acquisition. To address these challenges, this paper presents semantically enhanced models to enable reasoning through resolving part of commonsense ambiguity. The proposed models enhance in a knowledge graph embedding framework for knowledge base completion. Experimental results show the effectiveness of the new semantic models in commonsense reasoning.

引用

页码：1014 / 1021

页数：8

共 51 条

[1]

[Anonymous], 2011, P 25 AAAI C ART INT

[2]

[Anonymous], 2013, P 2013 C N AM CHAPTE

[3]

[Anonymous], 2012, Proceedings of the 21st international conference on World Wide Web

[4]

[Anonymous], 2015, EMNLP

[5]

[Anonymous], 2015, P AAAI FLAIRS

[6]

[Anonymous], 2015, P 2015 C EMP METH NA

[7]

[Anonymous], 2004, WWW '04, DOI DOI 10.1145/988672.988687

[8]

[Anonymous], 2013, ADV NEURAL INF PROCE

[9]

[Anonymous], 2015, P 2015 C EMP METH NA

[10]

[Anonymous], 2014, P C EMP METH NAT LAN

← 1 2 3 4 5 6 →