SpatialTech: Bruno Martins

On Tuesday, November 17, 2020, The UCSB forum on spatial technology presents

Challenges in resolving place names over text

 

Bruno Martins

University of Lisbon

11:30 a.m. Tuesday, November 17, 2020 | Zoom*

Abstract:

Toponym resolution concerns the disambiguation of place names in textual documents, envisioning the support for applications such as geographical search or the mapping of textually encoded information. Place names are first recognized through a named entity recognition model, and the disambiguation is then achieved by associating each of the place references to a unique position on the Earth’s surface, e.g., through the assignment of geospatial coordinates. The toponym resolution task is particularly challenging, given that place references are highly ambiguous (i.e., distinct locations can share the same place name, and multiple names can be used to refer to the same place). In this talk, I will discuss techniques for toponym resolution, with a particular emphasis on a novel deep learning approach. Contrarily to most previous methods, the novel approach does not involve matching references in the text against entries in a gazetteer, instead directly predicting geospatial coordinates. In brief, the neural network architecture considers multiple inputs (e.g.,the toponym to disambiguate together with the surrounding words), leveraging pre-trained contextual word embeddings for modeling the textual data. The intermediate representations are then used to predict a probability distribution over possible geospatial regions, and finally to predict the coordinates for the input toponym. I will present evaluation results over different types of corpora (e.g., modern newswire text or historical documents), and I will discuss the impact of model extensions related to (i) the use of external information concerning geophysical terrain properties, including information on terrain development or elevation, among others, and (ii) additional training data collected from Wikipedia articles, to guide and further help with model training.

Bio:

Bruno Martins is an assistant professor at the Computer Science and Engineering Department of Instituto Superior Técnico of the University of Lisbon (IST/UL), and a researcher at the Information and Decision Support Systems Lab of INESC-ID, where he works on problems related to the general areas of information retrieval, text mining, and the geographical information sciences. He received his MSc and PhD degrees from the Faculty of Sciences of the University of Lisbon, both in Computer Science. Bruno has been involved in several research projects related to geospatial aspects in information access and retrieval, and he has accumulated significant expertise in addressing challenges at the intersection of language technologies, machine learning, and the geographical information sciences. He and his students have worked on many different application areas, and he is proudest of the many PhD/MSc students who have graduated under his supervision and are now building wonderful careers.

Material:
SpatialTech-Bruno-Martins

The objectives of the Spatial Technology presentations are to exchange ideas and promote discussion and interaction within the spatial technology community

Please contact Karen Doehner, kdoehner@spatial.ucsb.edu or Emmanuel Papadakis epd@ucsb.edu, to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial technologies.

*This talk is a part of the spatial series Knowledge Representation and GeoHumanities; upon registration, you can access all the talks of the series using the provided link.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

SpatialTech: Ben Adams

On Tuesday, October 20, 2020, The UCSB forum on spatial technology presents

Contrastive explanations in GeoAI

 

Ben Adams

University of Canterbury

4:00 p.m. Tuesday, October 20, 2020 | Zoom

Abstract:

In the last few years interest in GeoAI has grown as newer machine learning techniques have shown success when applied to geographic problems. For the most part, this work has focused on training predictive deep learning models using large data sets. However, these models can be opaque and the reasoning behind why certain outcomes are predicted will not be clear to a human who might want to make informed decisions based on the predictions. In this talk my plan is not to discuss my own prior research but rather to introduce some recent research on explainable AI, and then to start a discussion within the GeoAI community about how we can build geographic AI systems that better explain their reasoning. In particular, I will focus on contrastive explanations and show how they might work for the kinds of use cases that have been presented at the Reasoning in GeoAI workshop, including crime analysis, travel behaviour modelling, and population projection.

Bio:

Ben Adams is a Senior Lecturer in the Department of Computer Science and Software Engineering at the University at Canterbury, New Zealand. He holds a PhD from the University of California, Santa Barbara and his research mainly focuses on exploring new ways of using computing technology to advance human understanding of the environment and world. His research includes the development of theories that explain how digital information reflects human conceptualization and building software systems that problem solving. Ben’s research interests include, indicatively, information retrieval, environmental narratives, spatial data science, spatial cognition and environmental narratives.

Material:
SpatialTech-Ben-Adams

The objectives of the Spatial Technology presentations are to exchange ideas and promote discussion and interaction within the spatial technology community

Please contact Karen Doehner, kdoehner@spatial.ucsb.edu or Emmanuel Papadakis epd@ucsb.edu, to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial technologies.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

SpatialTech: Seila Gonzalez Estrecha

On Tuesday, November 10, 2020, The UCSB forum on spatial technology presents

Enslaved.org: A knowledge representation in WikiBase of people, events and places in the historical slave trade

 

Seila Gonzalez Estrecha

Michigan State University

11:30 a.m. Tuesday, November 10, 2020 | Zoom*

Abstract:

The Enslaved.org project brings together multiple siloed datasets in a Wikibase representation of People, Places, and Events within the historical slave trade. A goal of this project is to develop a tool for scholars and the public to interact with this data to better understand the lives of enslaved Africans and their descendants. The vague definitions for places, with limited geographical information, presents challenges for this project including identifying the best approaches to represent the data. In this context, the meaning of place does not only include the concept of space but also the ethno-identity of many of those who were enslaved. This talk addresses the solutions taken by Enslaved.org in order to represent space, event, and people information and various challenges, including the technology behind the project and the motive to use Wikibase. It also covers the influence of places to disambiguate people records and the ontology alignment between the Wikibase graph and the owl ontology developed for Enslaved.org.

Bio:

Seila Gonzalez Estrecha manages and oversees the design and development of all software at Matrix, including all frontend and backend aspects of web applications, designing databases architecture, decision made for tools and technologies to be implemented, roadmap of software development of any Matrix products, identifying issues and common patterns, and developing standard operating procedures. She has experience implementing semantic web-based systems and standards for ontology-centered knowledge graphs, including work on knowledge graph modularization, ontology design patterns, interdisciplinary knowledge graph development, ontology alignment, data integration and implementation of SPARQL queries. Gonzalez directs the work of developers to ensure the adherence to best practices. She has experience in multiple programming languages and types of databases. Prior to coming to MSU, Gonzalez worked in the private sector as a java software engineer and GIS software developer.

Material:
SpatialTech-Seila Gonzalez-Estrecha

The objectives of the Spatial Technology presentations are to exchange ideas and promote discussion and interaction within the spatial technology community

Please contact Karen Doehner, kdoehner@spatial.ucsb.edu or Emmanuel Papadakis epd@ucsb.edu, to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial technologies.

*This talk is a part of the spatial series Knowledge Representation and GeoHumanities; upon registration, you can access all the talks of the series using the provided link.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

SpatialTech: Yingjie Hu

On Wednesday, October 21, 2020, the UCSB forum on spatial technology presents

Advancing Spatial and Textual Analysis with GeoAI

 

Yingjie Hu

University of Buffalo

11:30 a.m. Wednesday, October 21, 2020 | Zoom*

Abstract:

A rich amount of geographic information exists in unstructured texts, such as news articles, web pages, historical archives, and social media posts. Geoparsers are useful tools that extract location mentions from unstructured texts, thereby enabling spatial analysis of big textual data. In this talk, I will present our recent work in designing a unified platform for comparing geoparsers and building a deep learning-based model for improving toponym recognition from social media messages.

Bio:

Yingjie Hu is an Assistant Professor in the Department of Geography at the University at Buffalo (UB) and the National Center for Geographic Information and Analysis (NCGIA). He develops and applies spatial analysis, data mining, machine learning, and deep learning methods to address various geospatial problems in disaster response, public health, urban planning, and digital humanities. He received his Ph.D. from the Department of Geography at the University of California, Santa Barbara, and is an alumnus of the STKO Lab. He holds M.S. and B.S. degrees from East China Normal University. Hu is the author of over 50 peer-reviewed articles in top journals and conferences. He is passionate about teaching and conducting research on GIScience.

Material:
SpatialTech-Yingjie-Hu

The objectives of the Spatial Technology presentations are to exchange ideas and promote discussion and interaction within the spatial technology community

Please contact Karen Doehner, kdoehner@spatial.ucsb.edu or Emmanuel Papadakis epd@ucsb.edu, to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial technologies.

*This talk is a part of the spatial series Knowledge Representation and GeoHumanities; upon registration, you can access all the talks of the series using the provided link.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Karl Grossner

thinkspatial_logo
On Tuesday, October 27, 2020, the UCSB forum on spatial thinking presents

Representing Place for World Historical Gazetteer

 

Karl Grossner

University of Pittsburgh World History Center

11:30 a.m. Tuesday, October 27, 2020 | Zoom*

Abstract:

The recently launched World Historical Gazetteer (WHG) web platform aggregates contributions of information about named places drawn from historical source material by researchers studying the past in numerous humanities and social science fields. There are no constraints upon spatial or temporal extents, nor on scale of features, however, the project focus to date is on populated places, administrative units, natural geographic features, and regions of all kinds. Contributed datasets can be of any size.

To date, the WHG data stores hold records for about 1.8 million places having over 3 million name variants. Of these, only 60,000 have explicit temporal attributes; the remainder have been accessioned from the Getty Thesaurus of Geographic Names (TGN) and have unspecified temporal scope. We anticipate that the temporally scoped portion of WHG data will eventually grow to upwards of 10 million records. The project’s overarching goal is a free global resource useful for:

  1. geocoding of historical source materials, enabling mapping and spatial analysis of individual texts, corpora, and datasets
  2. linking historical research datasets and projects via shared references to places
  3. teaching, particularly geospatial perspectives in History
  4. via APIs, support for digital historical atlases and story maps

Linked Places format
As a data aggregation platform, WHG requires a standard contribution format. Researchers model data to suit their purposes, impacted by the nature of the source material and their conceptual model(s) of the phenomena being studied. We have developed the Linked Places format jointly with the Pelagios project, for use in both systems. Linked Places format is a hybrid: it is valid GeoJSON which has been extended with “when” objects for temporal scoping (GeoJSON-T), and it is valid JSON-LD v1.1, an RDF syntax.

Linked Places format enables relatively rich descriptions of places, including the temporal scoping of names, types, geometries, and relations with other places. We also developed a simpler and less expressive delimited text format, LP-TSV, and an automated transform is performed on ingest to WHG.

Toward Knowledge Representation
In this talk, Grossner will give an overview of Linked Places format, and the somewhat unorthodox path taken in development of its conceptual model, syntax, and supporting ontology. That path reflects the way that ontologies can emerge as working systems are developed, not as an afterthought, but as a product of investigating the entities and relations of a domain as the many variations of entities and properties “in the wild” present themselves.

Bio:

Karl Grossner is an independent GIScience researcher working to develop novel models, standard formats, and semantically-enabled software and systems supporting the emerging genre of digital historical atlases. Broadly, his research interest concern “computing place.” A co-founder of the GeoHumanities SIG within the Alliance for Digital Humanities Organizations (2013), Grossner is an active member of that global and trans-disciplinary community. From 2017 to the present, Grossner has served as Technical Director of the World Historical Gazetteer project at the University of Pittsburgh’s World History Center (whgazetteer.org).

After earning his Ph.D. in Geography at Santa Barbara in 2010, Grossner remained at the Center for Spatial Studies for a year, co-leading the NSF-funded TeachSpatial project (teachspatial.org) with Donald Janelle, the Center’s Program Director at the time. Following that, he worked for five years as a digital humanities research developer at Stanford University, building several significant interactive scholarly web applications in partnership with faculty members. Grossner’s side projects in recent years include GeoJSON-T, a temporal extension to the GeoJSON standard, and Linked Paths, experimental web software for representing, sharing, and analyzing data about historical geographic movement, including journeys, flows, and named routes.

Material:
ThinkSpatial-Grossner

The objectives of the ThinkSpatial brown-bag presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Marcela Suarez (amsuarez@ucsb.edu), Karen Doehner (kdoehner@spatial.ucsb.edu), or Emmanuel Papadakis (epd@ucsb.edu), to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

*This talk is a part of the spatial series Knowledge Representation and GeoHumanities; upon registration, you can access all the talks of the series using the provided link.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Nicola Guarino

thinkspatial_logo
On Tuesday, October 13, 2020, The UCSB forum on spatial thinking presents

Events and their (Spatial) Context: On the Semantics of Locative Modifiers

 

Nicola Guarino

ISTC-CNR Laboratory for Applied Ontology, Trento

9:00 a.m. Tuesday, October 13, 2020 | Zoom*

Abstract:

The notion of event is intimately connected to that of context. Describing an event means not just saying what happened, but also specifying how it happened, by adding details (generically called modifiers) that often involve the broader context where the event occurred. These modifiers often express locative information. But what are we referring to, when we add a locative modifier? This is an issue that has been investigated in the literature on linguistic semantics (especially by Claudia Maienborn), and is still rather open. Consider for instance “Maradona signed the contract in Argentina” versus “Maradona signed the contract on the last page.” While in the first case the modifier clearly denotes the location of the signature event, in the second case it refers to the location of something else. Similarly, in “John kissed Mary on the boat” the semantics of the locative modifier is clear, but in “John kissed Mary on the cheek” the semantics is different. In this talk, I will present a novel theory of events that explains these phenomena in terms of relationships between the modifier and the event’s context. It is a sort of microscopic approach based on the Aristotelian theory of change, according to which the actual subjects of change are individual qualities inhering in the participants, and not the participants themselves. In this view, an event (in its simplest form) is a single quality manifestation, i.e., the occurrence of a change (or unchanged) with respect to one of its qualities. More generally, ordinary events are clusters of quality manifestations, consisting of a focus accounting for what happens, and an internal context accounting for how it happens. Event kinds provide criteria to carve up events from the broader context by determining their focus and their internal context.

Bio:

Nicola Guarino is a retired research associate at the Institute of Cognitive Sciences and Technologies of the Italian National Research Council (ISTC-CNR), and former director of the ISTC-CNR Laboratory for Applied Ontology (LOA) based in Trento. Since 1991 he has been playing a leading role in the ontology field, developing a strongly interdisciplinary approach that combines together Computer Science, Philosophy, and Linguistics. The impact of such an approach is testified by a long list of widely cited papers and many keynote talks and tutorials in major conferences involving different communities. Among the most well-known results of his lab, the OntoClean methodology and the DOLCE foundational ontology. Guarino has been the founder and editor-in-chief (with Mark Musen, Stanford University) of the Applied Ontology journal, founder and former president of the International Association for Ontology and its Applications (IAOA), and editorial board member of Int. Journal of Semantic Web and Information Systems and Journal of Data Semantics. He is also a founding member of the Italian Association for Artificial Intelligence and fellow of the European Association for Artificial Intelligence (EurAI).

On the theoretical side, Guarino’s current research interests are focusing on the ontological foundations of knowledge representation and conceptual modeling and specifically the ontology of events and relationships (collaborating with Giancarlo Guizzardi to the new version of the UFO ontology), while on the application side his research is focusing on enterprise modeling and the ontology of economics. He is also interested in leveraging ontological analysis and semantic technologies to improve cognitive transparency, social accountability, and the participatory governance of artificial intelligence artifacts.

Material:
ThinkSpatial-Nicola-Guarino

The objectives of the ThinkSpatial presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Karen Doehner, kdoehner@spatial.ucsb.edu or Emmanuel Papadakis epd@ucsb.edu, to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

*This talk is a part of the spatial series Knowledge representation and GeoHumanities; upon registration, you can access all the talks of the series using the provided link.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

Series of themed spatial events

Spatial Series

 

The Center for Spatial Studies organizes series of Spatial Thinking (ThinkSpatial) and Spatial Technology (SpatialTech) events around a particular theme of interest to spatial communities. Every series runs over one semester and it is distributed in several sessions per month focusing on the theories, concepts, applications and technologies of the current theme.

Please contact Karen Doehner, kdoehner@spatial.ucsb.edu or Rui Zhu ruizhu@ucsb.edu, to review and schedule possible discussion topics or presentations that share your disciplinary interest with the running theme.

Series 2020–2021

(also available on our Google Calendar)

Fall '20: Knowledge Representation and GeoHumanities
Speakers from a variety of disciplines will deliver talks to communicate interdisciplinary ideas, methods, and technologies about the exciting topic of GeoHumanities. The objective is to study the challenges of representing the spatial knowledge of human phenomena and explore how spatial studies can embrace broader perspectives of space and place that are not bound to existing models or technologies. Read more.

Series: Knowledge Representation and GeoHumanities

For Fall Quarter 2020–2021, the Center for Spatial Studies will host a series of virtual spatial events under the theme:

Knowledge Representation and GeoHumanities

This series of spatial events will study the impact of Knowledge Representation and GIScience in the Geospatial Turn of Humanities.

Topic

Humanities stands for the academic disciplines that study aspects of human society and culture. Although intertwined by definition, the true power of interdisciplinary research in humanities was witnessed with the intersection of digital technologies. Computing led to the development of Digital Humanities (DH) providing not only the tools to digitize phenomena but also revolutionized the methodological focus of the comprising disciplines in the lines of knowledge representation, moving from descriptive representations reflecting individual perspectives to evidence-based, interconnected knowledge structures. Ontologies enhanced DH with the ability to formalize and reason with information about human phenomena. The interoperability afforded by ontologies enabled the exchange of information between systems, as well as enrichment with knowledge from various scientific fields which would seem near impossible in the past.

Humanities have a long tradition of investigating the analysis of place and space. The need for experimentation and the challenge of describing changes in human and social life without considering the impact of the involved spatial components led to the GeoSpatial Turn of Humanities. GeoHumanities allow the exploration of spatial methods and technologies in collaboration with Geographic Information Science opening new pathways of experimental research in the theoretical gulfs of Humanities. Fusing mixed theoretical methods with knowledge representation guidelines and modern spatial technologies enables a holistic approach to the study of place and space. Spatial studies can aid humanities to describe complex elusive phenomena by leveraging the special nature of spatial information and adopting methods and tools in Geographic Information Science (GIScience) that are already being used for critical reflection. GIScience, on the other hand, and GIS tools can be introduced and adjusted to subaltern understandings and conceptions of space that go beyond traditional cartographic paradigms, such as imaginary or vague places, as well as, complexities of time.

We aim to communicate interdisciplinary ideas, methods, and technologies about the exciting topic of GeoHumanities. The sessions will focus on a variety of challenges related to the knowledge representation of phenomena starting with the fundamental question, “what happens where?” In addition, it will explore ways to inform and transform spatial studies in order to embrace broader perspectives of space and place that are not bound to existing models or technologies.


The Knowledge Representation and Geohumanities speaker series is a joint effort of the Center for Spatial Studies and the NSF-funded KnowWhereGraph project.

Access and Participation

Please contact Karen Doehner (kdoehner@spatial.ucsb.edu) or Rui Zhu (ruizhu@ucsb.edu) if you would like to share your research in this series of events, in order to review and schedule possible topics.

If you would like to attend the event, please register here. Please note that upon registration you can attend any of the events using the same access link that will be sent to you.

Sessions

DateSpeakerAffiliationTopic
September 17, 2020Martin DoerrInstitute of Computer Science
Foundation for Research and Technology - Hellas
ThinkSpatial: Identifiable Individuals and Reality
What Do We Describe and Why?
October 13, 2020Nicola GuarinoInstitute of Cognitive Sciences and Technologies of the
Italian National Research Council
ThinkSpatial: Events and their (spatial) context: on the semantics of locative modifiers
October 21, 2020 Yingjie HuUniversity of BuffaloSpatialTech: Advancing spatial and textual analysis with GeoAI
October 27, 2020Karl GrossnerUniversity of Pittsburgh World History CenterThinkSpatial: Representing Place for World Historical Gazetteer.
November 10, 2020Seila Gonzalez EstrechaMichigan State UniversitySpatialTech: Enslaved.org: A knowledge representation in WikiBase of people, events and places in the historical slave trade
November 17, 2020Bruno MartinsUniversity of LisbonSpatialTech: Challenges in resolving place names over text.
November 24, 2020Patricia Murrieta-FloresLancaster UniversityThinkSpatial: Subaltern Spatial Thinking: Towards a decolonial approach to spatial technologies.

ThinkSpatial: Martin Doerr

thinkspatial_logo
On Thursday, September 17, 2020, The UCSB forum on spatial thinking presents

Identifiable Individuals and Reality
What Do We Describe and Why

 

Dr. Martin Doerr

Foundation for Research and Technology – Hellas (FORTH)

10:00 a.m. Thursday, September 17, 2020 | Zoom link*

Abstract:

Data of empirical-descriptive sciences, such as cultural heritage studies, geography, geology, biodiversity are usually kept in predicate-logic based information systems that refer to things in reality by unique identifiers. This can only work, if the referred features or phenomena, in reality, are distinct and can diachronically be identified in the same way by independent observers without a dialogue between them. In this presentation, we argue that only a smaller part of the features in our environment is sufficiently distinct over a useful time-span to form “identifiable individuals.” Different ontological categories can provide specific criteria about how parts of reality can be subdivided into “identifiable individuals” that turn out to be useful for modeling the behavior of reality as a result of observation, rather than convention, the so-called ontological individuation. We demonstrate (1) that there are always cases in which individuality is undecidable basically within all such categories, (2) that multiple individuals may overlap in substance in characteristic ways, and (3) that no such individual has precise spatiotemporal boundaries due to a variety of causes.

We argue that the kinds of conditions allowing for ontological individuation have widely not been studied, as well as what properties make phenomena not suited for individuation, such as clouds, stages of growth, flowing matter, and so forth. We further propose that the description of delimited situations in such systems, be it after observation or in prediction, needs to relate to identifiable individuals as reference. This epistemic individuation inherits the indeterminacy of the individuals of reference. We further propose that many kinds of scientific description of reality are an approximation that can be better processed via outer bounds. As a practical application, we show how adequate individuation criteria can substantially reduce the ambiguity of spatiotemporal gazetteers.

Bio:

Dr. Martin Doerr is a Research Director at the Information Systems Laboratory and honorary head of the Centre for Cultural Informatics of the Institute of Computer Science, FORTH. He has been leading the development of systems for knowledge representation and terminology, metadata, and content management. He has been leading or participating in a series of national and international projects for cultural information systems. His long-standing interdisciplinary work and collaboration with the International Council of Museums on modeling cultural-historical information have resulted besides others in an ISO Standard, ISO21127:2006, a core ontology for the purpose of schema integration across institutions.

Material:
ThinkSpatial2020-MartinDoerr

The objectives of the ThinkSpatial presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

* Please contact Karen Doehner, kdoehner@spatial.ucsb.edu or Emmanuel Papadakis epd@ucsb.edu, to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking. If you are participating from outside the UCSB community, please also ask for access credentials.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

Semantic Technology for Geographic Question Answering (GIScience 2021)

Workshop Overview

Please occasionally check back for updates and announcements.

geoQAThis half-day workshop at GIScience 2021 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

OrganizerAffiliation
Martin TomkoInfrastructure Engineering, University of Melbourne, AU
Simon ScheiderDepartment of Human Geography and Planning, Utrecht University, NL
Manolis KoubarakisDepartment of Informatics and Telecommunications, National and Kapodistrian University of Athens, GR
Sara LafiaDepartment 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

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 – 13:00):

  • Introduction (9:00 – 9:10)
  • Keynote: Questions in information system design and discussion (9:10 – 9:30)
  • Demos (9:30 – 10:15)
  • Coffee break (10:15 – 10:45)
  • Lightning talks: 3 minutes each, based on position papers (10:45 – 11:30)
  • Breakout groups: geoQA challenges – vocabularies, architectures, corpora (11:30 – 12:15)
  • Plenum discussion (12:15 – 13:00)
  • Lunch (13:00 – 14:00)