A Vector Semantics Approach to the Geoparsing Disambiguation Task for Texts in Spanish

9 pages•Published: November 4, 2019

Filomeno Alcántara, Alejandro Molina and Victor Muñiz

Abstract

Nowadays, online news sources generate continuous streams of information that includes references to real locations. Linking these locations to coordinates in a map usually requires two steps involving the named entity: extraction and disambiguation. In past years, efforts have been devoted mainly to the first task. Approaches to location disambiguation include knowledge-based, map-based and data-driven methods. In this paper, we present a work in progress for location disambiguation in news documents that uses a vector-semantic representation learned from information sources that include events and geographic descriptions, in order to obtain a ranking for the possible locations. We will describe the proposed method and the results obtained so far, as well as ideas for future work.

Keyphrases: doc2vec, embeddings, geoparsing, location disambiguation, nlp

In: Oscar S. Siordia, José Luis Silván Cárdenas, Alejandro Molina-Villegas, Gandhi Hernandez, Pablo Lopez-Ramirez, Rodrigo Tapia-McClung, Karime González Zuccolotto and Mario Chirinos Colunga (editors). Proceedings of the 1st International Conference on Geospatial Information Sciences, vol 13, pages 47-55.

Links:	https://easychair.org/publications/paper/KbMg
	https://doi.org/10.29007/pl5h

BibTeX entry

@inproceedings{iGISc2019:Vector_Semantics_Approach_Geoparsing,
  author    = {Filomeno Alcántara and Alejandro Molina and Victor Muñiz},
  title     = {A Vector Semantics Approach to the Geoparsing Disambiguation Task for Texts in Spanish},
  booktitle = {Proceedings of the 1st International Conference on Geospatial Information Sciences},
  editor    = {Oscar S. Siordia and José Luis Silván Cárdenas and Alejandro Molina-Villegas and Gandhi Hernandez and Pablo Lopez-Ramirez and Rodrigo Tapia-McClung and Karime González Zuccolotto and Mario Chirinos Colunga},
  series    = {Kalpa Publications in Computing},
  volume    = {13},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2515-1762},
  url       = {/publications/paper/KbMg},
  doi       = {10.29007/pl5h},
  pages     = {47-55},
  year      = {2019}}

Download PDF Open PDF in browser