Advertisement

Evaluating the Effectiveness of Embeddings in Representing the Structure of Geospatial Ontologies

  • Federico DasseretoEmail author
  • Laura Di Rocco
  • Giovanna Guerrini
  • Michela Bertolotto
Conference paper
Part of the Lecture Notes in Geoinformation and Cartography book series (LNGC)

Abstract

Nowadays word embeddings are used for many natural language processing (NLP) tasks thanks to their ability of capturing the semantic relations between words. Word embeddings have been mostly used to solve traditional NLP problems, such as question answering, textual entailment and sentiment analysis. This work proposes a new way of thinking about word embeddings that exploits them in order to represent geographical knowledge (e.g., geographical ontologies). We also propose metrics for evaluating the effectiveness of an embedding with respect to the ontological structure on which it is created both in an absolute way and with reference to its application within geolocation algorithms.

Keywords

Geospatial ontologies Word embeddings NLP Embedding evaluation Geo-term similarity 

References

  1. Bakarov A (2018) A survey of word embeddings evaluation methods. arXiv:1801.09536
  2. Baroni M, Dinu G, Kruszewski G (2014) Don’t count, predict! a systematic comparison of context-counting vs. context-predicting semantic vectors. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pp 238–247Google Scholar
  3. Bengio Y et al (2003) A neural probabilistic language model. J Mach Learn Res 3:1137–1155Google Scholar
  4. Bojanowski P et al (2017) Enriching word vectors with subword information. Trans Assoc Comput Linguist 5:135–146CrossRefGoogle Scholar
  5. Di Rocco L (2018) The role of geographic knowledge in sub-city level geolocation algorithms. PhD thesis. Dibris, Università degli Studi di GenovaGoogle Scholar
  6. Dredze M, Osborne M, Kambadur P (2016) Geolocation for twitter: timing matters. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 1064–1069Google Scholar
  7. Faruqui M et al (2016) Problems with evaluation of word embeddings usingword similarity tasks. In: Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, pp 30–35Google Scholar
  8. Griffiths TL, Tenenbaum JB, Steyvers M (2007) Topics in semantic representation. Psychol Rev 114(2):211–244CrossRefGoogle Scholar
  9. Gruber TR (1993) A translation approach to portable ontology specifications. Knowl Acquis 5(2):199–220CrossRefGoogle Scholar
  10. Harris ZS (1954) Distributional structure. WORD 10(23):146–162CrossRefGoogle Scholar
  11. Jia Y et al (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp 675–678Google Scholar
  12. Kejriwal M, Szekely P (2017) Neural embeddings for populated geonames locations. The Semantic Web - ISWC 2017, pp 139–146Google Scholar
  13. Krioukov D et al (2010) Hyperbolic geometry of complex networks. Phys Rev E 82(3):036106-01–036106-18Google Scholar
  14. Mikolov T et al (2013) Efficient estimation of word representations in vector space. In: ICLR WorkshopGoogle Scholar
  15. Nayak N, Angeli G, Manning CD (2016) Evaluating word embeddings using a representative suite of practical tasks. In: Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, pp 19–23Google Scholar
  16. Nickel M, Kiela D (2017) Poincaré embeddings for learning hierarchical representations. Adv Neural Inf Process Syst 30:6338–6347Google Scholar
  17. Nickel M, Kiela D (2018) Learning continuous hierarchies in the Lorentz model of hyperbolic geometry. In: Proceedings of the 35th International Conference on Machine Learning, pp 3776–3785Google Scholar
  18. Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp 1532–1543Google Scholar
  19. Sala F et al (2018) Representation tradeoffs for hyperbolic embeddings. In: Proceedings of the 35th International Conference on Machine Learning, pp 4460–4469Google Scholar
  20. Sayeed AB, Greenberg C, Demberg V (2016) Thematic fit evaluation: an aspect of selectional preferences. In: Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, pp 99–105Google Scholar
  21. Schnabel T et al (2015) Evaluation methods for unsupervised word embeddings. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp 298–307Google Scholar
  22. Stadler C et al (2012) LinkedGeoData: a core for a web of spatial open data. Semant Web 3(4):333–354Google Scholar
  23. Wang Q et al (2017) Knowledge graph embedding: a survey of approaches and applications. IEEE Trans Knowl Data Eng 29(12):2724–2743CrossRefGoogle Scholar
  24. Zheng X, Han J, Sun A (2018) A survey of location prediction on Twitter. IEEE Trans Knowl Data Eng 30(11):1652–1671CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Federico Dassereto
    • 1
    Email author
  • Laura Di Rocco
    • 1
  • Giovanna Guerrini
    • 1
  • Michela Bertolotto
    • 2
  1. 1.Università di Genova, DIBRISGenovaItaly
  2. 2.School of Computer ScienceUniversity College DublinDublinIreland

Personalised recommendations