Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings

05/19/2023
by   Mattia Atzeni, et al.
0

Entity linking methods based on dense retrieval are an efficient and widely used solution in large-scale applications, but they fall short of the performance of generative models, as they are sensitive to the structure of the embedding space. In order to address this issue, this paper introduces DUCK, an approach to infusing structural information in the space of entity representations, using prior knowledge of entity types. Inspired by duck typing in programming languages, we propose to define the type of an entity based on the relations that it has with other entities in a knowledge graph. Then, porting the concept of box embeddings to spherical polar coordinates, we propose to represent relations as boxes on the hypersphere. We optimize the model to cluster entities of similar type by placing them inside the boxes corresponding to their relations. Our experiments show that our method sets new state-of-the-art results on standard entity-disambiguation benchmarks, it improves the performance of the model by up to 7.9 F1 points, outperforms other type-aware approaches, and matches the results of generative models with 18 times more parameters.

READ FULL TEXT

page 8

page 16

research
08/28/2019

Explore Entity Embedding Effectiveness in Entity Retrieval

This paper explores entity embedding effectiveness in ad-hoc entity retr...
research
09/25/2020

AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding

Recent advances in Knowledge Graph Embed-ding (KGE) allow for representi...
research
02/03/2018

DeepType: Multilingual Entity Linking by Neural Type System Evolution

The wealth of structured (e.g. Wikidata) and unstructured data about the...
research
05/18/2021

Relation Classification with Entity Type Restriction

Relation classification aims to predict a relation between two entities ...
research
01/02/2021

Modeling Fine-Grained Entity Types with Box Embeddings

Neural entity typing models typically represent entity types as vectors ...
research
04/18/2022

TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval

Entity retrieval–retrieving information about entity mentions in a query...
research
06/17/2021

LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking

Entity linking (EL), the task of disambiguating mentions in text by link...

Please sign up or login with your details

Forgot password? Click here to reset