Workshop: Semantic Technology for Geographic Question Answering (GIScience 2020)

Workshop Overview

This half-day workshop at GIScience 2020 is meant to attract participants with a research interest in geographic question-answering (geoQA). This workshop focuses on geoQA both from a theoretical and a practical hands-on perspective. It is a unique opportunity to bring together GIScientists interested in diverse aspects of the problem at the early stages in the study of human spatial/place-based question-answering behaviour and QA systems.

This workshop will enable participants to demonstrate and compare early systems, corpora and approaches, and identify suitable directions for future research, including the collection of gold-standard corpora, task and scale specific QA system design (e.g. in-vehicle spatial interaction, instruction QA, factoid GeoQA). The workshop will enable the exchange of geoQA technology and ideas, as well as strive to identify the main challenges in geoQA. Novel challenges include spatial question parsers and corresponding grammars, the establishment of corpora and gold standards, the identification of spatial concepts in questions, and the special role that the geospatial Semantic Web and geo-analytical workflows play in geoQA.

Event Organizers and Affiliations

Organizer    Affiliation
Martin Tomko    Infrastructure Engineering, University of Melbourne, AU
Simon Scheider    Department of Human Geography and Planning, Utrecht University, NL
Manolis Koubarakis    Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, GR
Sara Lafia    Department of Geography, University of California Santa Barbara, US

For questions, please contact: Sara Lafia (slafia@ucsb.edu)

Topic

Question-answering (QA) is a form of verbal, dialogue-based interaction with information gaining ground in commercial services, such as smart assistants. It is enabling the most natural interaction with information thus far limited to human-to-human interaction – speech. It is particularly important in situations where the user is unable to operate via tactile interfaces, such as when driving, manipulating objects, or when the user is sight-impaired. Research on the different technical and conceptual challenges of QA has surged in information science, including phrase analysis, phrase mappings to entities in a database, entity disambiguation, and the construction of formal queries from questions. Question-answering approaches include knowledge-based (KB QA) and document-based question answering (DB QA). The former exploits reasoning on structured knowledge bases to infer factoid answers, e.g., from linked data stores. The latter extracts answers from text documents.

Since Geography and spatial relationships are an important part of numerous human-asked questions, geographic question answering (geoQA) has recently become an area of intensive research interest, both from a document as well as a knowledge centric view. This includes foundational research on the form and concepts of spatial questions and answers, geographic question corpora, geoQA interfaces, dialogue and information relevance related to specific tasks (incl. Wayfinding instructions), as well as research in enabling technology, including geographic query extensions over knowledge graphs and geo-analytical workflow composition.

Related Work:

• Hamzei, E., Li, H., Vasardani, M., Baldwin, T., Winter, S., & Tomko, M. (2020). Place Questions and Human-Generated Answers: A Data Analysis Approach. In P. Kyriakidis, D. Hadjimitsis, D. Skarlatos, & A. Mansourian (Eds.), Geospatial Technologies for Local and Regional Development (pp. 3–19). Springer International Publishing.
• Hamzei, E., Winter, S., & Tomko, M. (2019). Initial Analysis of Simple Where-Questions and Human-Generated Answers (Short Paper). In 14th International Conference on Spatial Information Theory (COSIT 2019). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik.
• Lafia, S., Xiao, J., Hervey, T., & Kuhn, W. (2019). Talk of the Town: Discovering Open Public Data via Voice Assistants (Short Paper). In 14th International Conference on Spatial Information Theory (COSIT 2019). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik.
• Lobry, S., Marcos, D., Murray, J., & Tuia, D. (2020). RSVQA: Visual Question Answering for Remote Sensing Data. arXiv preprint arXiv:2003.07333.
  Punjani, D., Karalis, N., Lange, C., Pantazi, D., Papaloukas, C., Stamoulis, G., Singh, K., Both, A., Koubarakis, M., Angelidis, I., Bereta, K., Beris, T., Bilidas, D., & Ioannidis, T. (2018). Template-Based Question Answering over Linked Geospatial Data. Proceedings of the 12th Workshop on Geographic Information Retrieval – GIR’18, 1–10.
• Scheider, S., Ballatore, A., & Lemmens, R. (2018). Finding and sharing GIS methods based on the questions they answer. International Journal of Digital Earth, 0(0), 1–20.
• Scheider, S., & Ballatore, A. (2018). Semantic typing of linked geoprocessing workflows. International Journal of Digital Earth, 11(1), 113-138.
  Scheider, S., & Tomko, M. (2016). Knowing whether spatio-temporal analysis procedures are applicable to datasets. In Formal Ontology in Information Systems (Vol. 283, pp. 67-80). IOS Press.

Contributions

We welcome contributions in the following two forms:

1. Position papers. Papers should be in pdf format, using the GIScience article template. They should be no longer than 2 pages (including references), and will be presented at the workshop in the form of a 5-minute lightning talk in the first half of the day.
2. Corpus datasets or QA tools. Both may be presented and tested in the hands-on/tutorial session in the second half of the day.

Submissions may be about (but are not limited to) the following topics:

• geoQA tasks and spatial question types
• Conceptual foundations of geoQA
• geoQA question corpora and answer datasets
• geoQA metrics and validation approaches
• Knowledge systems and ontologies for geoQA
• Document datasets and retrieval systems for geoQA
• Machine learning for geoQA
• Phrase analysis, grammars and NLP for geoQA
• Entity disambiguation and georeferencing for geoQA
• Reasoners and algorithms for geoQA
• What makes geoQA special, as compared to QA?
• Comparison of geoQA approaches and systems

Workshop contributions will be submitted via EasyChair (further details to come).

Important Dates

• Workshop contributions due: TBD (AoE, i.e., UTC-12)
• Notification of acceptance: TBD
• Early-bird registration ends: July 31, 2020
• Camera-ready papers due: TBD
• Workshop date: TBD (announcement pending conference rescheduling)

Schedule (tentative)

Half-day morning session (9:00 a.m.–1:00 p.m.):

• Introduction (9:00-9:10 a.m.)
• Keynote: Questions in information system design and discussion (9:10–9:30 a.m.)
• Demos (9:30–10:15 a.m.)
• Coffee break (10:15–10:45 a.m.)
• Lightning talks: 3 minutes each, based on position papers (10:45–11:30 a.m.)
• Breakout groups: geoQA challenges – vocabularies, architectures, corpora (11:30 a.m.–12:15 p.m.)
• Plenum discussion (12:15–1:00 p.m.)
• Lunch (1:00–2:00 p.m.)