The LEILAS project offers to develop research on the identification and the standardization of geographical entities. The project will develop technology that allows for an automatic recognition of references to geographic entities in web documents (such as countries, regions, cities, addresses…) and to give them real-life information.
Systems of geographic placement have already invaded our world and have changed the lives of many individuals; for example, the GPS, automobile navigation systems, mobile devices such as digital cameras with an incorporated GPS, etc… Over the past few years these systems have also become available via web services and web applications addressed to companies and to the public (Viamichelin, Mappy, Google Maps, Yellow Pages, etc…). What’s more, it is still very difficult to link the Web with physical systems of geographical placement. As a matter of fact, the Web is still lined with pages written in “natural language” and the names of places, addresses, points of interests, etc… found within these pages corresponding to a “manually written text”. LEILAS proposes to fill this gap by effectuating searches on the identification and the geo-referencing of named geographical entities just as they appear in the text written by humans. LEILAS will define the algorithms that will note each location, address, point of interest in a text with exact real-life information. The results of this search will be integrated into the ensemble of services / portals that will bring, to different users of the Web, a navigation experience enriched by three dimensional locations.
Innovation with LEILAS
In the LEILAS project, innovation resides principally in the use of natural language treatment and semantics for the identification of geographical entities found in texts. Their integration with the geographical information system reaches precision in the phases of identification and localization.
LEILAS proposes a group of innovative services allowing different users, individuals, companies or site administrators, to take the most advantage of Web 2.0 and to navigate information in a different way. The following three types of solutions will be studied:
- The MyPlaces portal: the user indicates several web pages of his or her choice and the portal offers the possibility to “manipulate” the geographical references contained within these pages. This three dimensional referencing will give the user, for example, a trip outline, personalized tour guides, automatic linking to web directories such as the yellow pages, hyperlinks towards zones of stocked information such as Wikipedia.
- The MyBiz portal: this offers the user the possibility to find commercial information in a geographical zone such as, for example, local productions, local transporters, the unemployment rate, the possibility of finance for entrepreneurs, etc… These services will also be integrated with novelties associated with a specific geographic zone at a given moment
- The NELocalize service: a B2B web service that offers Web site administrators the possibility to easily geo-localize the individuals consulting their sites. In the long-run, the service could transform into one service offering aggregators large volumes of content. All of the B2C portals will offer translation services improving inter-language comprehension, which is fundamental in domains such as tourism and finance.
VISEO’s role in LEILAS
VISEO is principally in charge of according contact details to real-life entities detected in texts as well as create the interface between the online texts, the linguistic treatment and the geographical information system. This is an online project with the interest of the VISEO group installed on mobile devices.
The five partners of the LEILAS project come from three different countries: France, Germany and Italy.
For more information go to http://www.leilas.eu/
Before joining the VISEO group, Frédérique SEGOND was Principal Scientist and manager of the Parsing and Semantics area (ParSem) at the Xerox Research Centre Europe. She joined Xerox as a research scientist in 1993 and worked on LOCOLEX, an intelligent dictionary lookup (European project COMPASS). Afterwards, within the PARGRAM (Parallel Grammars) project, she was responsible for the design and implementation of a French Lexical Functional Grammar (LFG). She then led the Lexical Sense Disambiguation LSD project where she worked on the EAGLES, ROMANSEVAL and EuroWordNet projects.
Throughout her research career she has developed, worked and coordinated about twenty collaborative research projects such as ALADIN, Europeanna, CACAO and Galateas.
Frédérique earned a PhD in Applied Mathematics at the Ecole des Hautes Etudes in Socil Sciences in Paris where she implemented categorical French grammar at IBM-France. After a one year post-doc at IBM-Watson in Yorktown working on the links between syntax and semantics, she was in charge of starting a research and teaching activity in a French Telecom school.
Frederique is co-author of six books, over 50 scientific papers and 5 patents. She belongs to several scientific committees. She is a member of the CONTINT steering committee of the French National Agency for Research (ANR), President of the Association for Computational Linguistics (ATALA), member of the ELRA board (European Language Resources Association), member of the board of the University Stendhal, and also provides scientific expertise to the European Commission. She is also on the “qualification list” of Professors of the University of Paris 7.