Abstract
Recent years have witnessed a rapid increase in Question Answering (QA) research and products in both academic and industry. However, geographic question answering remained nearly untouched although geographic questions account for a substantial part of daily communication. Compared to general QA systems, geographic QA has its own uniqueness, one of which can be seen during the process of handling unanswerable questions. Since users typically focus on the geographic constraints when they ask questions, if the question is unanswerable based on the knowledge base used by a QA system, users should be provided with a relaxed query which takes distance decay into account during the query relaxation and rewriting process. In this work, we present a spatially explicit translational knowledge graph embedding model called TransGeo which utilizes an edge-weighted PageRank and sampling strategy to encode the distance decay into the embedding model training process. This embedding model is further applied to relax and rewrite unanswerable geographic questions. We carry out two evaluation tasks: link prediction as well as query relaxation/rewriting for an approximate answer prediction task. A geographic knowledge graph training/testing dataset, DB18, as well as an unanswerable geographic query dataset, GeoUQ, are constructed. Compared to four other baseline models, our TransGeo model shows substantial advantages in both tasks.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Where the answer can vary between 63,000 and 10 depending on the conceptualization of Lake.
- 2.
Note that in many knowledge graphs, a triple can include a datatype property as the relation where the tail is a literal. In our work, we do not consider these kind of triple as they are not used in any major current KG embedding model. We will use head (h), relation (r), and tail(t) when discussing embeddings and subject (s), predicate (p), object (o) when discussing Semantic Web knowledge graphs to stay in line with the literature from both fields.
- 3.
We ignore ASK, CONSTRUCT, and DESCRIBE queries here as they are not typically used for question answering, and, thus, also not considered in related work.
- 4.
We leave the fact that interaction depends on the travel mode and related issues for further work. Similarity, due to the nature of existing knowledge graphs, we use point data to represent places despite the problems this may introduce. Work on effectively integrating linestrings, polygons, and topology into Web-scale knowledge graphs is ongoing (Regalia et al. 2017).
- 5.
- 6.
- 7.
- 8.
References
Bennett B, Mallenby D, Third A (2008) An ontology for grounding vague geographic terms. In: FOIS, vol 183, pp 280–293
Berant J, Chou A, Frostig R, Liang P (2013) Semantic parsing on freebase from question-answer pairs. In: Proceedings of the 2013 conference on empirical methods in natural language processing, pp 1533–1544
Bordes A, Usunier N, Garcia-Duran A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data. Adv Neural Inf Process Syst 2787–2795
Chen D, Fisch A, Weston J, Bordes A (2017) Reading wikipedia to answer open-domain questions. In: Proceedings of the 55th annual meeting of the association for computational linguistics (Volume 1: long papers), vol 1, pp 1870–1879
Chen W, Fosler-Lussier E, Xiao N, Raje S, Ramnath R, Sui D (2013) A synergistic framework for geographic question answering. In: 2013 IEEE seventh international conference on semantic computing (ICSC), IEEE, pp 94–99
Elbassuoni S, Ramanath M, Weikum G (2011) Query relaxation for entity-relationship search. In: Extended semantic web conference. Springer, Berlin, pp 62–76
Firth JR (1957) A synopsis of linguistic theory, 1930–1955. Studies linguist Anal
Fokou G, Jean S, Hadjali A, Baron M (2017) Handling failing rdf queries: from diagnosis to relaxation. Knowl Inf Syst 50(1):167–195
Hamilton W, Bajaj P, Zitnik M, Jurafsky D, Leskovec J (2018) Embedding logical queries on knowledge graphs. Adv Neural Inf Process Syst 2027–2038
Laurent D, Séguéla P, Nègre S (2006) QA better than IR?. In: Proceedings of the workshop on multilingual question answering. Association for Computational Linguistics, pp 1–8
Liang C, Berant J, Le Q, Forbus KD, Lao N (2017) Neural symbolic machines: learning semantic parsers on freebase with weak supervision. In: Proceedings of the 55th annual meeting of the association for computational linguistics (Volume 1: long papers), vol 1, pp 23–33
Liang C, Norouzi M, Berant J, Le QV, Lao N (2018) Memory augmented policy optimization for program synthesis and semantic parsing. Adv Neural Inf Process Syst 10014–10026
Lin Y, Liu Z, Sun M, Liu Y, Zhu X (2015) Learning entity and relation embeddings for knowledge graph completion. AAAI 15:2181–2187
Mai G, Janowicz K, He C, Liu S, Lao N (2018) POIReviewQA: a semantically enriched POI retrieval and question answering dataset. In: Proceedings of the 12th workshop on geographic information retrieval, ACM, p 5
Mai G, Janowicz K, Yan B (2018) Support and centrality: learning weights for knowledge graph embedding models. In: International conference on knowledge engineering and knowledge management. Springer, Berlin, pp 212–227
Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. Adv Neural Inf Process Syst 3111–3119
Miller A, Fisch A, Dodge J, Karimi A-H, Bordes A, Weston J (2016) Key-value memory networks for directly reading documents. In: Empirical methods in natural language processing (EMNLP), pp 1400–1409
Pasupat P, Liang P (2015) Compositional semantic parsing on semi-structured tables. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (Volume 1: Long Papers), vol 1, pp 1470–1480
Pulla VS, Jammi CS, Tiwari P, Gjoka M, Markopoulou A (2013) Questcrowd: a location-based question answering system with participation incentives. In: 2013 IEEE conference on computer communications workshops (INFOCOM WKSHPS), IEEE, pp 75–76
Rajpurkar P, Jia R, Liang P (2018) Know what you don’t know: unanswerable questions for SQuAD. arXiv:1806.03822
Rajpurkar P, Zhang J, Lopyrev K, Liang P (2016) SQuAD: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp 2383–2392
Regalia B, Janowicz K, McKenzie G (2017) Revisiting the representation of and need for raw geometries on the linked data web. In: LDOW@ WWW
Scheider S, Ballatore A, Lemmens R (2018) Finding and sharing GIS methods based on the questions they answer. Int J Digit Earth 1–20
Wang M, Wang R, Liu J, Chen Y, Zhang L, Qi G (2018) Towards empty answers in sparql: Approximating querying with rdf embedding. In: International semantic web conference. Springer, Berlin, pp 513–529
Wang Q, Mao Z, Wang B, Guo L (2017) Knowledge graph embedding: a survey of approaches and applications. IEEE Trans Knowl Data Eng 29(12):2724–2743
Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. AAAI 14:1112–1119
Yan B, Janowicz K, Mai G, Gao S (2017) From itdl to place2vec: reasoning about place type similarity and relatedness by learning embeddings from augmented spatial contexts. In: Proceedings of the 25th ACM SIGSPATIAL international conference on advances in geographic information systems, ACM, p 35
Yang F, Nie J, Cohen WW, Lao N (2017) Learning to organize knowledge with n-gram machines. arXiv:1711.06744
Yih W-t, Richardson M, Meek C, Chang M-W, Suh J (2016) The value of semantic parse labeling for knowledge base question answering. In: Proceedings of the 54th annual meeting of the association for computational linguistics (Volume 2: short papers), vol 2, pp 201–206
Zhang L, Zhang X, Feng Z (2018) TrQuery: an embedding-based framework for recommanding sparql queries. arXiv:1806.06205
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Mai, G., Yan, B., Janowicz, K., Zhu, R. (2020). Relaxing Unanswerable Geographic Questions Using A Spatially Explicit Knowledge Graph Embedding Model. In: Kyriakidis, P., Hadjimitsis, D., Skarlatos, D., Mansourian, A. (eds) Geospatial Technologies for Local and Regional Development. AGILE 2019. Lecture Notes in Geoinformation and Cartography. Springer, Cham. https://doi.org/10.1007/978-3-030-14745-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-14745-7_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-14744-0
Online ISBN: 978-3-030-14745-7
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)