Row-less Universal Schema

04/21/2016
by   Patrick Verga, et al.
0

Universal schema jointly embeds knowledge bases and textual patterns to reason about entities and relations for automatic knowledge base construction and information extraction. In the past, entity pairs and relations were represented as learned vectors with compatibility determined by a scoring function, limiting generalization to unseen text patterns and entities. Recently, 'column-less' versions of Universal Schema have used compositional pattern encoders to generalize to all text patterns. In this work we take the next step and propose a 'row-less' model of universal schema, removing explicit entity pair representations. Instead of learning vector representations for each entity pair in our training set, we treat an entity pair as a function of its relation types. In experimental results on the FB15k-237 benchmark we demonstrate that we can match the performance of a comparable model with explicit entity pair representations using a model of attention over relation types. We further demonstrate that the model per- forms with nearly the same accuracy on entity pairs never seen during training.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/18/2016

Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema

Universal schema predicts the types of entities and relations in a knowl...
research
11/19/2015

Multilingual Relation Extraction using Compositional Universal Schema

Universal schema builds a knowledge base (KB) of entities and relations ...
research
03/29/2021

Multi-facet Universal Schema

Universal schema (USchema) assumes that two sentence patterns that share...
research
04/12/2019

OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference

In this paper, we consider advancing web-scale knowledge extraction and ...
research
01/23/2023

WDC Products: A Multi-Dimensional Entity Matching Benchmark

The difficulty of an entity matching task depends on a combination of mu...
research
01/18/2013

Latent Relation Representations for Universal Schemas

Traditional relation extraction predicts relations within some fixed and...
research
01/16/2013

Learning New Facts From Knowledge Bases With Neural Tensor Networks and Semantic Word Vectors

Knowledge bases provide applications with the benefit of easily accessib...

Please sign up or login with your details

Forgot password? Click here to reset