Geographic reference analysis for geographic document querying F.Bilhaut, T.Charnois, P.Enjalbert & Y.Mathet {bilhaut, charnois, enjalbert,

Slides:



Advertisements
Similar presentations
Multilinguality & Semantic Search Eelco Mossel (University of Hamburg) Review Meeting, January 2008, Zürich.
Advertisements

© Johan Bos November 2005 Question Answering Lecture 1 (two weeks ago): Introduction; History of QA; Architecture of a QA system; Evaluation. Lecture 2.
Week 3.  Is the Tropic of Capricorn north or south of the equator?  What are the names of the 7 continents of the Earth?
NOUZONVILLE IN EUROPE. Europe seen from the sky France within Europe.
Probabilistic Language Processing Chapter 23. Probabilistic Language Models Goal -- define probability distribution over set of strings Unigram, bigram,
Geography Of France. Objectives Identify France on a blank map of Europe. How do France’s borders protect it? What is the weak point in France’s border?
Map Skills.
The Bulgarian National Corpus and Its Application in Bulgarian Academic Lexicography Diana Blagoeva, Sia Kolkovska, Nadezhda Kostova, Cvetelina Georgieva.
Spatial Mining.
Automatic Acquisition of Fuzzy Footprints Steven Schockaert, Martine De Cock, Etienne E. Kerre.
1 Entity Ranking Using Wikipedia as a Pivot (CIKM 10’) Rianne Kaptein, Pavel Serdyukov, Arjen de Vries, Jaap Kamps 2010/12/14 Yu-wen,Hsu.
GTECH 201 Lecture 05 Storing Spatial Data. Leftovers from Last Session From data models to data structures Chrisman’s spheres ANSI Sparc The role of GIScience.
Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang National Central University
1 D. Bekhouche/ Y. Pollet/ B. Grilheres/ X. Denis University of Salford, UK 06/24/2004 PSI Rouen Perception System Information 9 th International Conference.
The Geographic Perspective: Social Science Aspects
Economic Development in a Developed Economy – France. France is one of the most developed economies in the world and this is shown in the following statistics:
Design and Implementation of a Geographic Search Engine Alexander Markowetz Yen-Yu Chen Torsten Suel Xiaohui Long Bernhard Seeger.
Yuliya Morozova Institute for Informatics Problems of the Russian Academy of Sciences, Moscow.
The Geography of France “la géographie de la France” By Marc, Pierre, Hélène, and Robert.
The Tourism Geography of France. Learning Objectives 1.Appreciate the social and economic changes that have taken place in France and understand their.
The OIE’s work in setting sanitary standards Dr Sarah Kahn International Trade Department IPC Symposium February 2007 Geneva.
How Geographers See the World
BIENVENUE A avec votre animatrice Neighbor Countries Major Rivers Mountain Ranges Major Cities 1 Major Cities 2 Bodies of Water.
It is located in both the Western and Eastern Hemispheres. France is a country in Europe. It is situated completely in the Northern Hemisphere Longitude:
The Problem Finding information about people in huge text collections or on-line repositories on the Web is a common activity Person names, however, are.
Probabilistic Model for Definitional Question Answering Kyoung-Soo Han, Young-In Song, and Hae-Chang Rim Korea University SIGIR 2006.
GEOGRAPHY How can we describe our world?. THE FIVE THEMES OF GEOGRAPHY 1. Location: where places are located on the earth’s surface. 2. Place: Physical.
ATLANTIC AREA O.P. 4TH CALL FOR PROPOSAL SEARCH FOR PARTNERS Elegible Area: Spain (Galicia; Principado de Asturias; Cantabria; País Vasco; Comunidad Foral.
Social Studies Skill, p Which city is located near 30 degrees N, 30 degrees E? 3-2. What is another name for lines of longitude?
Extracting metadata for spatially- aware information retrieval on the internet Pual Clough Presented by Ali Khodaei CS 572.
Beyond Co-occurrence: Discovering and Visualizing Tag Relationships from Geo-spatial and Temporal Similarities Date : 2012/8/6 Resource : WSDM’12 Advisor.
Successful Regeneration in C21st Scotland - What will it take? A Personal View.
THINKING LIKE A GEOGRAPHER TEST REVIEW TEST IS ON FRIDAY, SEPT. 5!!!! STUDY STUDY STUDY!
Using a Named Entity Tagger to Generalise Surface Matching Text Patterns for Question Answering Mark A. Greenwood and Robert Gaizauskas Natural Language.
GUIDE : PROF. PUSHPAK BHATTACHARYYA Bilingual Terminology Mining BY: MUNISH MINIA (07D05016) PRIYANK SHARMA (07D05017)
Collocations and Information Management Applications Gregor Erbach Saarland University Saarbrücken.
Orleans France By Kendra Zellmer Casselberry. Location North Central France 130 kilometers southwest Paris. North Central France 130 kilometers southwest.
Analysing Miss O’Grady. Analysing Analysing is the interpretation of the data. It involves examining the data and giving meaning to it. When data has.
Using a Named Entity Tagger to Generalise Surface Matching Text Patterns for Question Answering Mark A. Greenwood and Robert Gaizauskas Natural Language.
ATLANTIC AREA O.P. 4TH CALL FOR PROPOSAL SEARCH FOR PARTNERS Elegible Area: Spain (Galicia; Principado de Asturias; Cantabria; País Vasco; Comunidad Foral.
National Technical University of Ukraine “Kiev Polytechnic Institute” Heat and energy design faculty Department of automation design of energy processes.
MOST Policy Documents A standardized approach for the dissemination & application of policy-relevant knowledge 1.Rationale for Standardized Approach 2.System.
Where we live.. Situation Lorient is one of the most important town in Brittany Lorient.
Find that place..  Find that content  Longitude, East is to the right, West is to the left of the Prime Meridian or 0 degrees  Latitude, North is going.
Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호 Text : FINDING OUT ABOUT Page. 182 ~ 251.
* Study the Ch 9 reading quiz * Notecards * Notes * The chapter.
Selecting Relevant Documents Assume: –we already have a corpus of documents defined. –goal is to return a subset of those documents. –Individual documents.
Jason W. Karl, Ph.D. Jeffrey K. Gillan Jason W. Karl, Ph.D. Jeffrey K. Gillan 23 October 2013 Ty Montgomery Richard Bliss Ty Montgomery Richard Bliss
Key Geography Concepts Chapter 1. Geography and Human Geography Three main geographic interests – Variation of Human and physical phenomena and humans.
Geography at Marlborough Primary School At Marlborough Primary School Geography continues to be delivered through a thematic approach. This approach allows.
Five Geographic Themes; Location
Latitude/Longitude.
Location To locate areas on Earth with precision, people drew a grid over maps and globes. One of the most important is the equator, which divides.
THE 5 THEMES OF GEOGRAPHY
France France.
Bell Ringer # 3 Text book page RA6 LOCATION: use cardinal directions
Geography at Marlborough Primary School
6 ~ GIR.
FRANCE France is an independent nation in Western Europe and the center of a large overseas administration. It is the third-largest European nation (after.
Maps and Regions Review
U.S. & N.C. Geography.
Integrated Middle School Curriculum
19 School Trust.
Geographic Forms.
THE 5 THEMES OF GEOGRAPHY
Information Retrieval and Web Design
Bell ringer: Composition Journal: Label Entry as “Geography 1” Describe the differences between Prattville and another city that you have visited or lived.
Town & Country.
Five Geographic Themes; Location
Map Skills Right On!.
Presentation transcript:

Geographic reference analysis for geographic document querying F.Bilhaut, T.Charnois, P.Enjalbert & Y.Mathet {bilhaut, charnois, enjalbert, GREYC, CNRS UMR 6072 University of Caen

The "GéoSem" project Passage extraction from geographical documents From a query to a ranked set of passages Queries are concerned with : - time - phenomenon - space

Excerpt from "Hérin" corpus From 1965 to 1985, the number of high-school students has increased by 70%, but at different rythms and intensities depending on academies and departments. Lower in South-West and Massif Central, moderate in Brittany and Paris, the rise has been considerable in Mid-West and Alsace. […] Also occurs the schooling duration increase which was more important in departments where, in the middle of the 60's, study continuation after primary school was far from beeing systematic.

Excerpt from "Hérin" corpus From 1965 to 1985, the number of high-school students has increased by 70%, but at different rythms and intensities depending on academies and departments. Lower in South-West and Massif Central, moderate in Brittany and Paris, the rise has been considerable in Mid-West and Alsace. […] Also occurs the schooling duration increase which was more important in departments where, in the middle of the 60's, study continuation after primary school was far from beeing systematic. Time

Excerpt from "Hérin" corpus From 1965 to 1985, the number of high-school students has increased by 70%, but at different rythms and intensities depending on academies and departments. Lower in South-West and Massif Central, moderate in Brittany and Paris, the rise has been considerable in Mid-West and Alsace. […] Also occurs the schooling duration increase which was more important in departments where, in the middle of the 60's, study continuation after primary school was far from beeing systematic. TimePhenomenon

Excerpt from "Hérin" corpus From 1965 to 1985, the number of high-school students has increased by 70%, but at different rythms and intensities depending on academies and departments. Lower in South-West and Massif Central, moderate in Brittany and Paris, the rise has been considerable in Mid-West and Alsace. […] Also occurs the schooling duration increase which was more important in departments where, in the middle of the 60's, study continuation after primary school was far from beeing systematic. TimePhenomenonSpace

Queries Which passages address educational difficulties in west of France in the 50's ? Which passages address variations of the number of pupils in rural areas ? Which passages address Calvados district?

Queries Which passages address educational difficulties in west of France in the 50's? Which passages address variations of the number of pupils in Paris area? Which passages address Calvados district?

Some Signifiant Spatial Expressions Paris in north of France from south of Loire Some seabord towns The quarter of The districts in north of France Fifteen All Some seabord towns of Normandy The most rural districts situated from south of Loire

The type "zone" a georeferenced area anchored in a named place Paris in north of France Normandy From Normandy to Alsace from south of Loire

The ‘LocGeo’ type Quant Type Zone qualification administrative Position named geo. entity The quarter of / districts in north of France Fifteen / All / Some seabordtowns of Normandy The most ruraldistricts situated from south of Loire Some seabord towns  The canonical form: [quantification]+[type]+[zone]

The ‘LocGeo’ type Quant Type Zone qualification administrative Position named geo. entity The quarter of / districts in north of France Fifteen / All / Some seabordtowns of Normandy The most ruraldistricts situated from south of Loire Some seabord towns quant type zone

Semantic Representation « Paris » zone: loc: internal egn: coord: ty_zone: town nom: Paris Long: Lat:

Semantic Representation « Some seabord towns in north of Normandy » locgeo: quant: type: zone: type: relative ty_zone: town geo: seabord nom: Normandy ty_zone: region loc: internal position: north egn:

Implementation and (first) Results  A tokenisation and a morphological analysis  A DCG to perform altogether syntactic and semantic analysis the grammar contains 160 rules an internal lexical base of 200 entries a gazetteer of named places (France)  9OO expressions recognised and analysed from a geographical corpus (200 text pages)  Good results but a precise and quantitative evaluation to be done

Semantic matching : Why ? a query corpora Text A Text B […] the northern half of France […] […] the south of a Bordeaux-Genève line […] "Which passages address Paris ?" […] In Paris and Toulouse […] […] In Ile de France region […] 1 3 2

Semantic matching : How ? Spatial compatibility : Is the zone denoted by the passage spatially compatible with the one of the query? (is there, at least, an intersection?) Relevance degree : if this zone is compatible, how relevant is it w.r.t.the query? - probability - granularity

Compatibility computation Q1) Which passages address Paris ? P1) […] the capital city […] P2) […] big cities in France. P3) […] the northern half of France […] P4) […] South of a Bordeaux-Genève line. YES NO gazetteer gazetteer + computation gis+computation

"the northern half of France"

"the south of a Bordeaux-Genève line"

Relevance degree (1) Quantification Query= "Calvados" (french district) P1= "The quarter of districts in north of France" P2= "All districts in north of France" P3= "Some districts in north of France" P4= "Fifteen districts in north of France" r=25% r=100% r=i/n=5/52=9.6% r=i/n=15/52=29% GIS rank

Relevance degree (2) Granularity "Basse Normandie" "Calvados" ’the northern half of France’ "Caen" country region district city "zone"

locgeo(locgeo:(det:Det..type:Type..Zone)) --> #prep, det(Det), type(Type), zone(Zone). det(Sem) --> [X],{lexique(X,[X|R],det,Sem)}. type(X) --> typeQualif(X). type(ty_zone:N) --> nomtype(N). typeQualif(ty_zone:N..Q) --> option, nomtype(N), #prep, qualif(Q). nomtype(Sem) --> [X], {lexique(X,[X|R],nom,Sem)}. zone(X)--> egn(X). egn(egn:(ty_zone:T..nom:Y..coord:C)) --> --> ls_lexiconExtDCG(np, type_sem:egn..type_zone:T..nom:Y..coord:C ). egn(egn:(ty_zone:T..nom:Y)) --> [X],{lexique(X,[X|R],np, type_sem:egn..type_zone:T..nom:Y)}.

lexique(quelque,[quelque],det,type_sem:relatif..type:relatif_qualifie..nb:'qualitatif:faible'). lexique(tout,[tout,le],det,type_sem:exhaustif). lexique(région,[région],nom,type_sem:zone(administrative)..nom_zone:région). lexique(ville,[ville],nom,type_sem:zone(administrative)..nom_zone:ville). Lexique('Bretagne',['Bretagne'], np,type_sem:egn..type_zone:région..nom:'Bretagne').