Entity Linking with a Paraphrase Flavor. Pershina, M., He, Y., & Grishman, R. abstract bibtex The task of Named Entity Linking is to link entity mentions in the document to their correct entries in a knowledge base and to cluster NIL mentions. Ambiguous, misspelled, and incomplete entity mention names are the main challenges in the linking process. We propose a novel approach that combines two state-of-the-art models — for entity disambiguation and for paraphrase detection — to overcome these challenges. We consider name variations as paraphrases of the same entity mention and adopt a paraphrase model for this task. Our approach utilizes a graph-based disambiguation model based on Personalized Page Rank, and then refines and clusters its output using the paraphrase similarity between entity mention strings. It achieves a competitive performance of 80.5% in B3+F clustering score on diagnostic TAC EDL 2014 data.
@article{pershina_entity_nodate,
title = {Entity {Linking} with a {Paraphrase} {Flavor}},
abstract = {The task of Named Entity Linking is to link entity mentions in the document to their correct entries in a knowledge base and to cluster NIL mentions. Ambiguous, misspelled, and incomplete entity mention names are the main challenges in the linking process. We propose a novel approach that combines two state-of-the-art models — for entity disambiguation and for paraphrase detection — to overcome these challenges. We consider name variations as paraphrases of the same entity mention and adopt a paraphrase model for this task. Our approach utilizes a graph-based disambiguation model based on Personalized Page Rank, and then refines and clusters its output using the paraphrase similarity between entity mention strings. It achieves a competitive performance of 80.5\% in B3+F clustering score on diagnostic TAC EDL 2014 data.},
language = {en},
author = {Pershina, Maria and He, Yifan and Grishman, Ralph},
pages = {5},
}
Downloads: 0
{"_id":"Fnr6yejm9DzAZCE28","bibbaseid":"pershina-he-grishman-entitylinkingwithaparaphraseflavor","author_short":["Pershina, M.","He, Y.","Grishman, R."],"bibdata":{"bibtype":"article","type":"article","title":"Entity Linking with a Paraphrase Flavor","abstract":"The task of Named Entity Linking is to link entity mentions in the document to their correct entries in a knowledge base and to cluster NIL mentions. Ambiguous, misspelled, and incomplete entity mention names are the main challenges in the linking process. We propose a novel approach that combines two state-of-the-art models — for entity disambiguation and for paraphrase detection — to overcome these challenges. We consider name variations as paraphrases of the same entity mention and adopt a paraphrase model for this task. Our approach utilizes a graph-based disambiguation model based on Personalized Page Rank, and then refines and clusters its output using the paraphrase similarity between entity mention strings. It achieves a competitive performance of 80.5% in B3+F clustering score on diagnostic TAC EDL 2014 data.","language":"en","author":[{"propositions":[],"lastnames":["Pershina"],"firstnames":["Maria"],"suffixes":[]},{"propositions":[],"lastnames":["He"],"firstnames":["Yifan"],"suffixes":[]},{"propositions":[],"lastnames":["Grishman"],"firstnames":["Ralph"],"suffixes":[]}],"pages":"5","bibtex":"@article{pershina_entity_nodate,\n\ttitle = {Entity {Linking} with a {Paraphrase} {Flavor}},\n\tabstract = {The task of Named Entity Linking is to link entity mentions in the document to their correct entries in a knowledge base and to cluster NIL mentions. Ambiguous, misspelled, and incomplete entity mention names are the main challenges in the linking process. We propose a novel approach that combines two state-of-the-art models — for entity disambiguation and for paraphrase detection — to overcome these challenges. We consider name variations as paraphrases of the same entity mention and adopt a paraphrase model for this task. Our approach utilizes a graph-based disambiguation model based on Personalized Page Rank, and then refines and clusters its output using the paraphrase similarity between entity mention strings. It achieves a competitive performance of 80.5\\% in B3+F clustering score on diagnostic TAC EDL 2014 data.},\n\tlanguage = {en},\n\tauthor = {Pershina, Maria and He, Yifan and Grishman, Ralph},\n\tpages = {5},\n}\n\n","author_short":["Pershina, M.","He, Y.","Grishman, R."],"key":"pershina_entity_nodate","id":"pershina_entity_nodate","bibbaseid":"pershina-he-grishman-entitylinkingwithaparaphraseflavor","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/groups/2244199/items?key=9pbdlqiip5aNXlOfkVSImlsv&format=bibtex&limit=100","dataSources":["mxP3KHaoaaFN8BHHH"],"keywords":[],"search_terms":["entity","linking","paraphrase","flavor","pershina","he","grishman"],"title":"Entity Linking with a Paraphrase Flavor","year":null}