Skip to content

Data and code of the paper "Unsupervised Entity Linking with Guided Summarization and Multiple-Choice Selection"

License

Notifications You must be signed in to change notification settings

JeffreyCh0/SumMC

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Unsupervised Entity Linking with Guided Summarization and Multiple-Choice Selection

This repository contains codes and datasets in the paper "Unsupervised Entity Linking with Guided Summarization and Multiple-Choice Selection" by Young-Min Cho, Li Zhang, and Chris Callison-Burch, on the Proceedings of EMNLP 2022.

Paper link: https://aclanthology.org/2022.emnlp-main.638/

SumMC

SumMC is a fully unsupervised entity linking model that first generates a guided summary of the contexts conditioning on the mention, and then casts the task to a multiple-choice problem where the model chooses an entity from a list of candidates.

WikiHow-Wikidata

WikiHow-Wikidata is a human-annotated dataset that links noun phrases in procedural texts from wikiHow to Wikidata entities.

About

Data and code of the paper "Unsupervised Entity Linking with Guided Summarization and Multiple-Choice Selection"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published