Predicting Relevance Scores for Triples from Type-Like Relations using Neural Embedding - The Cabbage Triple Scorer at WSDM Cup 2017.

Yael Brumer; Bracha Shapira; Lior Rokach; Oren Barkan

Predicting Relevance Scores for Triples from Type-Like Relations using Neural Embedding - The Cabbage Triple Scorer at WSDM Cup 2017.

Yael Brumer, Bracha Shapira, Lior Rokach, Oren Barkan

Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

The WSDM Cup 2017 Triple scoring challenge is aimed at calculating and assigning relevance scores for triples from type-like relations. Such scores are a fundamental ingredient for ranking results in entity search. In this paper, we propose a method that uses neural embedding techniques to accurately calculate an entity score for a triple based on its nearest neighbor. We strive to develop a new latent semantic model with a deep structure that captures the semantic and syntactic relations between words. Our method has been ranked among the top performers with accuracy - 0.74, average score difference - 1.74, and average Kendall's Tau - 0.35.
Comment: Triple Scorer at WSDM Cup 2017, see arXiv:1712.08081

Original language	English
Number of pages	5
Journal	CoRR
Volume	abs/1712.08359
State	Published - 2017

Bibliographical note

DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

Keywords

Information Retrieval
cs.IR

Access to Document

Cite this

@article{a0f3d54a85b747df9fcdbcec46fa192b,

title = "Predicting Relevance Scores for Triples from Type-Like Relations using Neural Embedding - The Cabbage Triple Scorer at WSDM Cup 2017.",

abstract = "The WSDM Cup 2017 Triple scoring challenge is aimed at calculating and assigning relevance scores for triples from type-like relations. Such scores are a fundamental ingredient for ranking results in entity search. In this paper, we propose a method that uses neural embedding techniques to accurately calculate an entity score for a triple based on its nearest neighbor. We strive to develop a new latent semantic model with a deep structure that captures the semantic and syntactic relations between words. Our method has been ranked among the top performers with accuracy - 0.74, average score difference - 1.74, and average Kendall's Tau - 0.35.Comment: Triple Scorer at WSDM Cup 2017, see arXiv:1712.08081",

keywords = "Information Retrieval, cs.IR",

author = "Yael Brumer and Bracha Shapira and Lior Rokach and Oren Barkan",

note = "DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",

year = "2017",

language = "אנגלית",

volume = "abs/1712.08359",

journal = "CoRR",

}

TY - JOUR

T1 - Predicting Relevance Scores for Triples from Type-Like Relations using Neural Embedding - The Cabbage Triple Scorer at WSDM Cup 2017.

AU - Brumer, Yael

AU - Shapira, Bracha

AU - Rokach, Lior

AU - Barkan, Oren

N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2017

Y1 - 2017

N2 - The WSDM Cup 2017 Triple scoring challenge is aimed at calculating and assigning relevance scores for triples from type-like relations. Such scores are a fundamental ingredient for ranking results in entity search. In this paper, we propose a method that uses neural embedding techniques to accurately calculate an entity score for a triple based on its nearest neighbor. We strive to develop a new latent semantic model with a deep structure that captures the semantic and syntactic relations between words. Our method has been ranked among the top performers with accuracy - 0.74, average score difference - 1.74, and average Kendall's Tau - 0.35.Comment: Triple Scorer at WSDM Cup 2017, see arXiv:1712.08081

AB - The WSDM Cup 2017 Triple scoring challenge is aimed at calculating and assigning relevance scores for triples from type-like relations. Such scores are a fundamental ingredient for ranking results in entity search. In this paper, we propose a method that uses neural embedding techniques to accurately calculate an entity score for a triple based on its nearest neighbor. We strive to develop a new latent semantic model with a deep structure that captures the semantic and syntactic relations between words. Our method has been ranked among the top performers with accuracy - 0.74, average score difference - 1.74, and average Kendall's Tau - 0.35.Comment: Triple Scorer at WSDM Cup 2017, see arXiv:1712.08081

KW - Information Retrieval

KW - cs.IR

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

VL - abs/1712.08359

JO - CoRR

JF - CoRR

ER -

Predicting Relevance Scores for Triples from Type-Like Relations using Neural Embedding - The Cabbage Triple Scorer at WSDM Cup 2017.

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this