@inproceedings{tam-etal-2019-optimal,
title = "Optimal Transport-based Alignment of Learned Character Representations for String Similarity",
author = "Tam, Derek and
Monath, Nicholas and
Kobren, Ari and
Traylor, Aaron and
Das, Rajarshi and
McCallum, Andrew",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1592",
doi = "10.18653/v1/P19-1592",
pages = "5907--5917",
abstract = "String similarity models are vital for record linkage, entity resolution, and search. In this work, we present STANCE{--}a learned model for computing the similarity of two strings. Our approach encodes the characters of each string, aligns the encodings using Sinkhorn Iteration (alignment is posed as an instance of optimal transport) and scores the alignment with a convolutional neural network. We evaluate STANCE{'}s ability to detect whether two strings can refer to the same entity{--}a task we term alias detection. We construct five new alias detection datasets (and make them publicly available). We show that STANCE (or one of its variants) outperforms both state-of-the-art and classic, parameter-free similarity models on four of the five datasets. We also demonstrate STANCE{'}s ability to improve downstream tasks by applying it to an instance of cross-document coreference and show that it leads to a 2.8 point improvement in B{\^{}}3 F1 over the previous state-of-the-art approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tam-etal-2019-optimal">
<titleInfo>
<title>Optimal Transport-based Alignment of Learned Character Representations for String Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="family">Tam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Monath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ari</namePart>
<namePart type="family">Kobren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Traylor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajarshi</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>String similarity models are vital for record linkage, entity resolution, and search. In this work, we present STANCE–a learned model for computing the similarity of two strings. Our approach encodes the characters of each string, aligns the encodings using Sinkhorn Iteration (alignment is posed as an instance of optimal transport) and scores the alignment with a convolutional neural network. We evaluate STANCE’s ability to detect whether two strings can refer to the same entity–a task we term alias detection. We construct five new alias detection datasets (and make them publicly available). We show that STANCE (or one of its variants) outperforms both state-of-the-art and classic, parameter-free similarity models on four of the five datasets. We also demonstrate STANCE’s ability to improve downstream tasks by applying it to an instance of cross-document coreference and show that it leads to a 2.8 point improvement in B\³ F1 over the previous state-of-the-art approach.</abstract>
<identifier type="citekey">tam-etal-2019-optimal</identifier>
<identifier type="doi">10.18653/v1/P19-1592</identifier>
<location>
<url>https://aclanthology.org/P19-1592</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>5907</start>
<end>5917</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Optimal Transport-based Alignment of Learned Character Representations for String Similarity
%A Tam, Derek
%A Monath, Nicholas
%A Kobren, Ari
%A Traylor, Aaron
%A Das, Rajarshi
%A McCallum, Andrew
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F tam-etal-2019-optimal
%X String similarity models are vital for record linkage, entity resolution, and search. In this work, we present STANCE–a learned model for computing the similarity of two strings. Our approach encodes the characters of each string, aligns the encodings using Sinkhorn Iteration (alignment is posed as an instance of optimal transport) and scores the alignment with a convolutional neural network. We evaluate STANCE’s ability to detect whether two strings can refer to the same entity–a task we term alias detection. We construct five new alias detection datasets (and make them publicly available). We show that STANCE (or one of its variants) outperforms both state-of-the-art and classic, parameter-free similarity models on four of the five datasets. We also demonstrate STANCE’s ability to improve downstream tasks by applying it to an instance of cross-document coreference and show that it leads to a 2.8 point improvement in B\³ F1 over the previous state-of-the-art approach.
%R 10.18653/v1/P19-1592
%U https://aclanthology.org/P19-1592
%U https://doi.org/10.18653/v1/P19-1592
%P 5907-5917
Markdown (Informal)
[Optimal Transport-based Alignment of Learned Character Representations for String Similarity](https://aclanthology.org/P19-1592) (Tam et al., ACL 2019)
ACL