By the same authors

Feature-Rich Networks for Knowledge Base Completion

Research output: Contribution to conferencePaper

Published copy (DOI)

Author(s)

Department/unit(s)

Conference

Conference55th Annual Meeting of the Association for Computational Linguistics
CountryCanada
CityVancouver
Conference date(s)30/07/174/08/17

Publication details

DatePublished - 30 Jul 2017
Number of pages6
Original languageEnglish

Abstract

We propose jointly modelling Knowledge Bases and aligned text with Feature-Rich
Networks. Our models perform Knowledge Base Completion by learning to represent and compose diverse feature types from partially aligned and noisy resources. We perform experiments on Freebase utilizing additional entity type information and syntactic textual relations. Our evaluation suggests that the proposed models can better incorporate side information than previously proposed combinations of bilinear models with convolutional neural networks, showing large improvements when scoring the plausibility of unobserved facts with associated textual mentions.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations