Optimal Transport-based Alignment of Learned Character Representations for String Similarity

Tam, Derek; Monath, Nicholas; Kobren, Ari; Traylor, Aaron; Das, Rajarshi; McCallum, Andrew

doi:10.48550/arxiv.1907.10165

Cited by 2 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…'Bill Clinton (President)' matching 'Presidency of Bill Clinton'), which learns true matchings from lists of positive and negative candidate pairs. Tam et al [34] have recently presented STANCE, a model for computing the similarity between two strings by encoding the characters of each of them, aligning the encodings using Sinkhorn Iteration, and scoring the alignments using a convolutional neural network.…”

Section: Related Workmentioning

confidence: 99%

A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching

Ardanuy¹,

Hosseini²,

McDonough³

et al. 2020

Preprint

View full text Add to dashboard Cite

Recognizing toponyms and resolving them to their real-world referents is required to provide advanced semantic access to textual data. is process is o en hindered by the high degree of variation in toponyms. Candidate selection is the task of identifying the potential entities that can be referred to by a previously recognized toponym.While it has traditionally received li le a ention, candidate selection has a signi cant impact on downstream tasks (i.e. entity resolution), especially in noisy or non-standard text. In this paper, we introduce a deep learning method for candidate selection through toponym matching, using state-of-the-art neural network architectures. We perform an intrinsic toponym matching evaluation based on several datasets, which cover various challenging scenarios (cross-lingual and regional variations, as well as OCR errors) and assess its performance in the context of geographical candidate selection in English and Spanish.

show abstract

Section: Related Workmentioning

confidence: 99%

A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching

Ardanuy¹,

Hosseini²,

McDonough³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Inventor mobility further complicates the use of contextual information for disambiguation. Much research has been done within the fields of economics, computer science and statistics to disambiguate inventor mentions in this situation (Trajtenberg and Shiff, 2008;Ferreira et al, 2012;Ventura et al, 2013;Li et al, 2014;Ventura et al, 2015;Kim et al, 2016;Yang et al, 2017;Morrison et al, 2017;Müller, 2017;Traylor et al, 2017;Balsmeier et al, 2018;Tam et al, 2019;Monath et al, 2019;Doherr, 2021).…”

Section: Introductionmentioning

confidence: 99%

Estimating the Performance of Entity Resolution Algorithms: Lessons Learned Through PatentsView.org

Binette¹,

York²,

Hickerson³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper introduces a novel evaluation methodology for entity resolution algorithms. It is motivated by PatentsView.org, a U.S. Patents and Trademarks Office patent data exploration tool that disambiguates patent inventors using an entity resolution algorithm. We provide a data collection methodology and tailored performance estimators that account for sampling biases. Our approach is simple, practical and principled -key characteristics that allow us to paint the first representative picture of PatentsView's disambiguation performance. This approach is used to inform PatentsView's users of the reliability of the data and to allow the comparison of competing disambiguation algorithms.

show abstract

Optimal Transport-based Alignment of Learned Character Representations for String Similarity

Cited by 2 publications

References 22 publications

A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching

A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching

Estimating the Performance of Entity Resolution Algorithms: Lessons Learned Through PatentsView.org

Contact Info

Product

Resources

About