@inproceedings{yang-etal-2018-collective,
title = "Collective Entity Disambiguation with Structured Gradient Tree Boosting",
author = "Yang, Yi and
Irsoy, Ozan and
Rahman, Kazi Shefaet",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-1071",
doi = "10.18653/v1/N18-1071",
pages = "777--786",
abstract = "We present a gradient-tree-boosting-based structured learning model for jointly disambiguating named entities in a document. Gradient tree boosting is a widely used machine learning algorithm that underlies many top-performing natural language processing systems. Surprisingly, most works limit the use of gradient tree boosting as a tool for regular classification or regression problems, despite the structured nature of language. To the best of our knowledge, our work is the first one that employs the structured gradient tree boosting (SGTB) algorithm for collective entity disambiguation. By defining global features over previous disambiguation decisions and jointly modeling them with local features, our system is able to produce globally optimized entity assignments for mentions in a document. Exact inference is prohibitively expensive for our globally normalized model. To solve this problem, we propose Bidirectional Beam Search with Gold path (BiBSG), an approximate inference algorithm that is a variant of the standard beam search algorithm. BiBSG makes use of global information from both past and future to perform better local search. Experiments on standard benchmark datasets show that SGTB significantly improves upon published results. Specifically, SGTB outperforms the previous state-of-the-art neural system by near 1{\%} absolute accuracy on the popular AIDA-CoNLL dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2018-collective">
<titleInfo>
<title>Collective Entity Disambiguation with Structured Gradient Tree Boosting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ozan</namePart>
<namePart type="family">Irsoy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazi</namePart>
<namePart type="given">Shefaet</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a gradient-tree-boosting-based structured learning model for jointly disambiguating named entities in a document. Gradient tree boosting is a widely used machine learning algorithm that underlies many top-performing natural language processing systems. Surprisingly, most works limit the use of gradient tree boosting as a tool for regular classification or regression problems, despite the structured nature of language. To the best of our knowledge, our work is the first one that employs the structured gradient tree boosting (SGTB) algorithm for collective entity disambiguation. By defining global features over previous disambiguation decisions and jointly modeling them with local features, our system is able to produce globally optimized entity assignments for mentions in a document. Exact inference is prohibitively expensive for our globally normalized model. To solve this problem, we propose Bidirectional Beam Search with Gold path (BiBSG), an approximate inference algorithm that is a variant of the standard beam search algorithm. BiBSG makes use of global information from both past and future to perform better local search. Experiments on standard benchmark datasets show that SGTB significantly improves upon published results. Specifically, SGTB outperforms the previous state-of-the-art neural system by near 1% absolute accuracy on the popular AIDA-CoNLL dataset.</abstract>
<identifier type="citekey">yang-etal-2018-collective</identifier>
<identifier type="doi">10.18653/v1/N18-1071</identifier>
<location>
<url>https://aclanthology.org/N18-1071</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>777</start>
<end>786</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collective Entity Disambiguation with Structured Gradient Tree Boosting
%A Yang, Yi
%A Irsoy, Ozan
%A Rahman, Kazi Shefaet
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F yang-etal-2018-collective
%X We present a gradient-tree-boosting-based structured learning model for jointly disambiguating named entities in a document. Gradient tree boosting is a widely used machine learning algorithm that underlies many top-performing natural language processing systems. Surprisingly, most works limit the use of gradient tree boosting as a tool for regular classification or regression problems, despite the structured nature of language. To the best of our knowledge, our work is the first one that employs the structured gradient tree boosting (SGTB) algorithm for collective entity disambiguation. By defining global features over previous disambiguation decisions and jointly modeling them with local features, our system is able to produce globally optimized entity assignments for mentions in a document. Exact inference is prohibitively expensive for our globally normalized model. To solve this problem, we propose Bidirectional Beam Search with Gold path (BiBSG), an approximate inference algorithm that is a variant of the standard beam search algorithm. BiBSG makes use of global information from both past and future to perform better local search. Experiments on standard benchmark datasets show that SGTB significantly improves upon published results. Specifically, SGTB outperforms the previous state-of-the-art neural system by near 1% absolute accuracy on the popular AIDA-CoNLL dataset.
%R 10.18653/v1/N18-1071
%U https://aclanthology.org/N18-1071
%U https://doi.org/10.18653/v1/N18-1071
%P 777-786
Markdown (Informal)
[Collective Entity Disambiguation with Structured Gradient Tree Boosting](https://aclanthology.org/N18-1071) (Yang et al., NAACL 2018)
ACL
- Yi Yang, Ozan Irsoy, and Kazi Shefaet Rahman. 2018. Collective Entity Disambiguation with Structured Gradient Tree Boosting. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 777–786, New Orleans, Louisiana. Association for Computational Linguistics.