Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding
C. Xiong, R. Power, und J. Callan. Proceedings of the 26th International Conference on World Wide Web, Seite 1271--1279. Republic and Canton of Geneva, Switzerland, International World Wide Web Conferences Steering Committee, (2017)
DOI: 10.1145/3038912.3052558
Zusammenfassung
This paper introduces Explicit Semantic Ranking (ESR), a new ranking technique that leverages knowledge graph embedding. Analysis of the query log from our academic search engine, SemanticScholar.org, reveals that a major error source is its inability to understand the meaning of research concepts in queries. To addresses this challenge, ESR represents queries and documents in the entity space and ranks them based on their semantic connections from their knowledge graph embedding. Experiments demonstrate ESR's ability in improving Semantic Scholar's online production system, especially on hard queries where word-based ranking fails.
Beschreibung
Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding
%0 Conference Paper
%1 xiong2017explicit
%A Xiong, Chenyan
%A Power, Russell
%A Callan, Jamie
%B Proceedings of the 26th International Conference on World Wide Web
%C Republic and Canton of Geneva, Switzerland
%D 2017
%I International World Wide Web Conferences Steering Committee
%K academic graph knowledge mag ranking research search semantic
%P 1271--1279
%R 10.1145/3038912.3052558
%T Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding
%U https://doi.org/10.1145/3038912.3052558
%X This paper introduces Explicit Semantic Ranking (ESR), a new ranking technique that leverages knowledge graph embedding. Analysis of the query log from our academic search engine, SemanticScholar.org, reveals that a major error source is its inability to understand the meaning of research concepts in queries. To addresses this challenge, ESR represents queries and documents in the entity space and ranks them based on their semantic connections from their knowledge graph embedding. Experiments demonstrate ESR's ability in improving Semantic Scholar's online production system, especially on hard queries where word-based ranking fails.
%@ 978-1-4503-4913-0
@inproceedings{xiong2017explicit,
abstract = {This paper introduces Explicit Semantic Ranking (ESR), a new ranking technique that leverages knowledge graph embedding. Analysis of the query log from our academic search engine, SemanticScholar.org, reveals that a major error source is its inability to understand the meaning of research concepts in queries. To addresses this challenge, ESR represents queries and documents in the entity space and ranks them based on their semantic connections from their knowledge graph embedding. Experiments demonstrate ESR's ability in improving Semantic Scholar's online production system, especially on hard queries where word-based ranking fails.},
acmid = {3052558},
added-at = {2017-07-19T11:42:31.000+0200},
address = {Republic and Canton of Geneva, Switzerland},
author = {Xiong, Chenyan and Power, Russell and Callan, Jamie},
biburl = {https://www.bibsonomy.org/bibtex/26ffa936e47f36fabb7f0b83927cbcec8/jaeschke},
booktitle = {Proceedings of the 26th International Conference on World Wide Web},
description = {Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding},
doi = {10.1145/3038912.3052558},
interhash = {d01442f3e3e9f5ab377630ca1f93bba7},
intrahash = {6ffa936e47f36fabb7f0b83927cbcec8},
isbn = {978-1-4503-4913-0},
keywords = {academic graph knowledge mag ranking research search semantic},
location = {Perth, Australia},
numpages = {9},
pages = {1271--1279},
publisher = {International World Wide Web Conferences Steering Committee},
series = {WWW '17},
timestamp = {2017-07-19T11:42:31.000+0200},
title = {Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding},
url = {https://doi.org/10.1145/3038912.3052558},
year = 2017
}