Download full text
(238.3Kb)
Citation Suggestion
Please use the following Persistent Identifier (PID) to cite this document:
https://nbn-resolving.org/urn:nbn:de:0168-ssoar-70719-0
Exports for your reference manager
Concept Embedding for Information Retrieval
[conference paper]
Abstract Concepts are used to solve the term-mismatch problem. However, we need an effective similarity measure between concepts. Word embedding presents a promising solution. We present in this study three approaches to build concepts vectors based on words vectors. We use a vector-based measure to estimate... view more
Concepts are used to solve the term-mismatch problem. However, we need an effective similarity measure between concepts. Word embedding presents a promising solution. We present in this study three approaches to build concepts vectors based on words vectors. We use a vector-based measure to estimate inter-concepts similarity. Our experiments show promising results. Furthermore, words and concepts become comparable. This could be used to improve conceptual indexing process.... view less
Keywords
information retrieval; indexing
Classification
Information Science
Free Keywords
Computation and Language; Machine Learning
Collection Title
Advances in Information Retrieval: 40th European Conference on IR Research, ECIR 2018, Grenoble, France, March 26-29, 2018 ; Proceedings
Editor
Pasi, Gabriella; Piwowarski, Benjamin; Azzopardi, Leif; Hanbury, Allan
Conference
40. European Conference on IR Research (ECIR). Grenoble, 2018
Document language
English
Publication Year
2018
Publisher
Springer International Publishing
City
Cham
Page/Pages
p. 563-569
Series
Lecture Notes in Computer Science (LNCS), 10772
DOI
https://doi.org/10.1007/978-3-319-76941-7_45
ISSN
1611-3349
ISBN
978-3-319-76941-7
Status
Postprint; peer reviewed
Licence
Deposit Licence - No Redistribution, No Modifications