Geographic information retrieval (GIR) or geographical information retrieval systems are search tools for searching the Web,

enterprise Enterprise (or the archaic spelling Enterprize) may refer to: Business and economics Brands and enterprises * Enterprise GP Holdings, an energy holding company * Enterprise plc, a UK civil engineering and maintenance company * Enterpris ...

documents, and mobile local search that combine traditional text-based queries with location querying, such as a

map A map is a symbolic depiction of interrelationships, commonly spatial, between things within a space. A map may be annotated with text and graphics. Like any graphic, a map may be fixed to paper or other durable media, or may be displayed on ...

or placenames. Like traditional

information retrieval Information retrieval (IR) in computing and information science is the task of identifying and retrieving information system resources that are relevant to an Information needs, information need. The information need can be specified in the form ...

systems, GIR systems index text and information from

structured Structuring, also known as smurfing in banking jargon, is the practice of executing financial transactions such as making bank deposits in a specific pattern, calculated to avoid triggering financial institutions to file reports required by law ...

and unstructured

document A document is a writing, written, drawing, drawn, presented, or memorialized representation of thought, often the manifestation of nonfiction, non-fictional, as well as fictional, content. The word originates from the Latin ', which denotes ...

s, and also augment those indices with geographic information. The development and engineering of GIR systems aims to build systems that can reliably answer queries that include a geographic dimension, such as "What wars were fought in Greece?" or "restaurants in Beirut". Semantic similarity and

word-sense disambiguation Word-sense disambiguation is the process of identifying which sense of a word is meant in a sentence or other segment of context. In human language processing and cognition, it is usually subconscious. Given that natural language requires ref ...

are important components of GIR. To identify place names, GIR systems often rely on

natural language processing Natural language processing (NLP) is a subfield of computer science and especially artificial intelligence. It is primarily concerned with providing computers with the ability to process data encoded in natural language and is thus closely related ...

or other

metadata Metadata (or metainformation) is "data that provides information about other data", but not the content of the data itself, such as the text of a message or the image itself. There are many distinct types of metadata, including: * Descriptive ...

to associate text

documents A document is a written, drawn, presented, or memorialized representation of thought, often the manifestation of non-fictional, as well as fictional, content. The word originates from the Latin ', which denotes a "teaching" or "lesson": ...

with locations. Such georeferencing,

geotagging Geotagging, or GeoTagging, is the process of adding geographical identification metadata to various media such as a geotagged photograph or video, websites, SMS messages, QR Codes or RgSSfeeds and is a form of geospatial metadata. This data ...

, and geoparsing tools often need databases of location names, known as

gazetteers A gazetteer is a geographical dictionary or directory used in conjunction with a map or atlas.Aurousseau, 61. It typically contains information concerning the geographical makeup, social statistics and physical features of a country, region, ...

GIR architecture

GIR involves extracting and resolving the meaning of locations in unstructured text. This is known as geoparsing. After identifying mentions of places and locations in text, a GIR system indexes this information for search and retrieval. GIR systems can commonly be broken down into the following stages: geoparsing, text and geographic indexing, data storage, geographic relevance ranking with respect to a geographic query and browsing results commonly with a map interface. Some GIR systems separate text indexing from geographic indexing, which enables the use of generic database joins, or multi-stage filtering, and others combine them for efficiency. GIR must manage several forms of uncertainty, including

semantic ambiguity In linguistics, an expression is semantically ambiguous when it can have multiple meanings. The higher the number of synonyms a word has, the higher the degree of ambiguity. Like other kinds of ambiguity, semantic ambiguities are often clarified by ...

of mentions of places in

natural language A natural language or ordinary language is a language that occurs naturally in a human community by a process of use, repetition, and change. It can take different forms, typically either a spoken language or a sign language. Natural languages ...

text and position precision.

GIR systems

* MetaCarta created and patented one of the first commercial products to offer GIR capabilities. * Frankenplace: a general-purpose geographic search engine. * Web-a-where

Study & Evaluation

The study of GIR systems has a rich history dating back to the 1970s and possibly earlier. See Ray Larson’s book ''Geographic information retrieval and spatial browsing'' for references to much of the pre-

Web Web most often refers to: * Spider web, a silken structure created by the animal * World Wide Web or the Web, an Internet-based hypertext system Web, WEB, or the Web may also refer to: Computing * WEB, a literate programming system created by ...

literature on GIR. In 2005 the Cross-Language Evaluation Forum added a geographic track, GeoCLEF. GeoCLEF was the first TREC-style evaluation forum for GIR systems and provided participants a chance to compare systems.

Applications

GIR has many applications in geoweb, neogeography, and mobile local search and has been a focus of many conferences, including the

ESRI Environmental Systems Research Institute, Inc., doing business as Esri (), is an American Multinational corporation, multinational geographic information system (GIS) software company headquartered in Redlands, California. It is best known for ...

Users Conferences and O'Reilly’s Where 2.0 conferences.

GIR architecture

GIR systems

Study & Evaluation

Applications

References

See also