2020 ECIR tutorial Text Meets Space: Geographic Content Extraction, Resolution, and Information Retrieval
This half-day tutorial will be divided into five sessions:
-
Geography and text: an introduction to the ways in which geographic concepts are reflected in natural language and in text;
-
Toponym recognition and resolution: key to most geographically inspired analysis are the use of place-names in text, their identification, disambiguation, and resolution to unique locations;
-
Geographic relevance and ranking: methods for incorporating geographic information in IR indexes and ranking algorithms. Discuss what is geographic relevance, and how it varies with context and application domain;
-
Applications: Concrete examples for the application of the introduced methods, in fields ranging from Digital Humanities to Web search, together with a discussion on requirements and their implications on algorithmic and data choices;
-
Future challenges: Where are the most likely applications of GIR in the future, and what are key societal and methodologically driven challenges; The first four sessions will each present fundamental challenges, a selection of examples from the state of the art, and include interactive exercises (computer and/or paper based) to illustrate basic concepts to participants.
We will be using two historical texts as our primary datasets in this tutorial: Samuel Johnson's travel writing about the islands of Scotland and the collection of writings from James Cook and Joseph Banks from their trips on the Endeavour to Australia and elsewhere. Both texts were written in English and published in the late eighteenth century.
-
Johnson, Samuel, 1709-1784, A journey to the western islands of Scotland, Oxford Text Archive, http://hdl.handle.net/20.500.12024/0076.
-
Hawkesworth, John, 1715?-1773.; Revere, Paul, 1735-1818, engraver. and Romans, Bernard, ca. 1720-ca. 1784, engraver., 2009, A new voyage, round the world, in the years 1768, 1769, 1770, and 1771; undertaken by order of His present Majesty, performed by, Captain James Cook, in the ship Endeavour, drawn up from his own journal, and from the papers of Joseph Banks, Esq. F.R.S. : And published by the special direction of the Right Honourable the Lords of the Admiralty. / By John Hawkesworth, L.L.D. and late director of the East-India Company. ; In two volumes: with cutts [sic] and a map of the whole navigation. ; Vol. I[-II]., Oxford Text Archive, http://hdl.handle.net/20.500.12024/N10511.
The txt and xml files have been provided by the Oxford Text Archive, and the xml files in particular were created through the Text Creation Partnership with Gale. Making the Eighteenth-Century Collections Online materials openly accessible and machine-readable, ECCO-TCP is a key corpus of historical texts in several languages.