Skip to Main content Skip to Navigation
Conference papers

Towards Spatial Word Embeddings

Abstract : Leveraging textual and spatial data provided in spatio-textual objects (eg., tweets), has become increasingly important in real-world applications, favoured by the increasing rate of their availability these last decades (eg., through smartphones). In this paper, we propose a spatial retrofitting method of word embeddings that could reveal the localised similarity of word pairs as well as the diversity of their localised meanings. Experiments based on the semantic location prediction task show that our method achieves significant improvement over strong baselines.
Document type :
Conference papers
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Friday, February 28, 2020 - 2:23:12 PM
Last modification on : Saturday, June 13, 2020 - 7:49:48 AM
Long-term archiving on: : Friday, May 29, 2020 - 3:19:09 PM


Files produced by the author(s)


  • HAL Id : hal-02494099, version 1
  • OATAO : 24752


Paul Mousset, Yoann Pitarch, Lynda Tamine-Lechani. Towards Spatial Word Embeddings. 41st European Conference on Information Retrieval (ECIR 2019), Apr 2019, Cologne, Germany. pp.53-61. ⟨hal-02494099⟩



Record views


Files downloads