Search Results for author: Joseph Fisher

Found 6 papers, 4 papers with code

Debiasing knowledge graph embeddings

no code implementations EMNLP 2020 Joseph Fisher, Arpit Mittal, Dave Palfrey, Christos Christodoulopoulos

It has been shown that knowledge graph embeddings encode potentially harmful social biases, such as the information that women are more likely to be nurses, and men more likely to be bankers.

Knowledge Graph Embeddings

REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking

1 code implementation19 Apr 2024 Nacime Bouziani, Shubhi Tyagi, Joseph Fisher, Jens Lehmann, Andrea Pierleoni

Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by closed information extraction (cIE).

Benchmarking coreference-resolution +11

ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking

3 code implementations NAACL (ACL) 2022 Tom Ayoola, Shubhi Tyagi, Joseph Fisher, Christos Christodoulopoulos, Andrea Pierleoni

The model is capable of generalising to large-scale knowledge bases such as Wikidata (which has 15 times more entities than Wikipedia) and of zero-shot entity linking.

 Ranked #1 on Entity Linking on WebQSP-WD (using extra training data)

Entity Disambiguation Entity Linking +1

Improving Entity Disambiguation by Reasoning over a Knowledge Base

3 code implementations NAACL 2022 Tom Ayoola, Joseph Fisher, Andrea Pierleoni

Recent work in entity disambiguation (ED) has typically neglected structured knowledge base (KB) facts, and instead relied on a limited subset of KB information, such as entity descriptions or types.

Entity Disambiguation

Measuring Social Bias in Knowledge Graph Embeddings

no code implementations5 Dec 2019 Joseph Fisher, Dave Palfrey, Christos Christodoulopoulos, Arpit Mittal

It has recently been shown that word embeddings encode social biases, with a harmful impact on downstream tasks.

Knowledge Graph Embeddings Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.