Index of /downloads/kbbridge

[ICO]NameLast modifiedSizeDescription

[PARENTDIR]Parent Directory   -  
[TXT]bootstrap.css 2013-03-01 00:26 124K 
[   ]oair2013.pdf 2013-03-21 17:35 344K 

KB Bridge - Entity Linking

KB Bridge

KB Bridge is an entity linking system which identifies named entities in free text and links them to entries in a semistructured knowledge base, such as Freebase or Wikipedia.

Developers: Jeff Dalton, Laura Dietz. Continued by Pat Verga



Publications

A Neighborhood Relevance Model for Entity Linking

Jeffrey Dalton and Laura Dietz

Entity Linking is the task of mapping a string in a document to its entity in a knowledge base. One of the crucial tasks is to identify disambiguating context; joint assignment models leverage the relationships within the knowledge base. We demonstrate how joint assignment models can be approximated with information retrieval. We introduce the neighborhood relevance model which uses relevance feedback techniques to identify the salience of entity context using cross-document evidence. We show that this model is more effective than local document models for ranking KB entities. Experiments on the TAC KBP entity linking task demonstrate that our model is the best performing system for strings that are linkable to the knowledge base.
[full paper .pdf]

Cite As

@inproceedings{Dalton-OAIR2013,
author = {Dalton, Jeffrey and Dietz, Laura},
booktitle = {Proceedings of the 10th International Conference in the RIAO series (OAIR), 2013},
title = {A Neighborhood Relevance Model for Entity Linking},
year = {2013}
}

Source Code

Code available on GitHub