Place name ambiguity is a sub-task of the more general problem of word sense disambiguation. Ide and Véronis [6] concisely define the problem of disambiguation as " matching the context of the instance of the word to be disambiguated with either information from an external knowledge source, or information about the contexts of the word derived from corpora ." Thus, a set of words identified as a place name must be matched to the specific location on the Earth's surface that the author was referring to. The main difference between place name disambiguation and other disambiguation problems is implicit topological and geographic relationships between locations can be exploited for disambiguation.

Saul Steinberg's most famous cartoon “View of the world from 9th Avenue” depicts the world as seen by self-absorbed New Yorkers. By analysing wikipediae of a range of different languages, we find that this particular fish-eye world view is ubiquitous and inherently part of human nature.By measuring the skew in the distribution of locations in different languages we can confirm the validity of plausible quantitative models. These models demonstrate convincingly that people all have similar world views: “We are all little Steinbergs.”Our Steinberg hypothesis allows the world view of specific people to be more accurately modelled; this will allow greater understanding of a person's discourse, either by someone else or automatically by a computer.

In this paper we provide some analysis of data fusion techniques employed at GeoCLEF 2008 to merge textual and geographic relevance. These methods are compared to our own experiments, where using our GIR system, Forostar, we show that an aggressive filter-based data fusion method can outperform a more sophisticated penalisation method.

Tagging has emerged as a popular means to annotate on-line objects such as bookmarks, photos and videos. Tags vary in semantic meaning and can describe different aspects of a media object. Tags describe the content of the media as well as locations, dates, people and other associated meta-data. Being able to automatically classify tags into semantic categories allows us to understand better the way users annotate media objects and to build tools for viewing and browsing the media objects. In this paper we present a generic method for classifying tags using third party open content resources, such as Wikipedia and the Open Directory. Our method uses structural patterns that can be extracted from resource meta-data. We describe the implementation of our method on Wikipedia using WordNet categories as our classification schema and ground truth. Two structural patterns found in Wikipedia are used for training and classification: categories and templates. We apply our system to classifying Flickr tags. Compared to a WordNet baseline our method increases the coverage of the Flickr vocabulary by 115%. We can classify many important entities that are not covered by WordNet, such as, London Eye, Big Island, Ronaldinho, geocaching and wii.

This paper describes an application of statistical co-occurrence techniques that built on top of a probabilistic image annotation framework is able to increase the precision of an image annotation system. We observe that probabilistic image analysis by itself is not enough to describe the rich semantics of an image. Our hypothesis is that more accurate annotations can be produced by introducing additional knowledge in the form of statistical co-occurrence of terms. This is provided by the context of images that otherwise independent keyword generation would miss. We applied our algorithm to the dataset provided by ImageCLEF 2008 for the Visual Concept Detection Task (VCDT). Our algorithm not only obtained better results but also it appeared in the top quartile of all methods submitted in ImageCLEF 2008.

This paper presents the work of the MMIS group at ImageCLEF 2008. The results for three tasks are presented: Visual Concept Detection Task (VCDT), ImageCLEFphoto and ImageCLEFwiki. We combine image annotations, CBIR, textual relevance and a geographic filter using our generic data fusion method. We also compare methods for BRF and clustering. Our top performing method in the VCDT enhances supervised learning by modifying probabilities based on a matrix that shows how terms appear together. Although it occurred in the top quartile of submitted runs, the enhancement did not provide a statistically significant improvement. In the ImageCLEFphoto task we demonstrate that evidence from image retrieval can provide a contribution to retrieval; however we are yet to find a way of combining text and image evidence in a way to provide an improvement over the baseline. Due to the relative performances of dierence evidences in ImageCLEFwiki and our failure to improve over a baseline we conclude that text is the dominant feature in this collection.

In this paper we present Forostar, our GIR system. Forostar augments a traditional IR VSM approach with geographic information. We detail our placename disambiguation and geographic relevance ranking methods, as well as how textual and geographic relevance assessments are combined. The paper concludes with an analysis of our results including significance testing where we show our baseline method, in fact, to be best. Finally we identify weaknesses in our approach and ways in which the system could be optimised and improved.

In this paper we present our Geographic Information Retrieval System, Forostar, and the results of three experiments. We compare two data fusion methods, and show that a simple geographic filter outperforms a penalty based system. We compare context based disambiguation to a default gazetteer and show no significant dierence. Finally we compare a unique geographic index to an ambiguous geographic index. The ambiguous index outperformed all other methods and was statistically significantly better than the baseline.

This paper describes the generation of a model capturing information on how placenames co-occur together. The advantages of the co-occurrence model over traditional gazetteers are discussed and the problem of placename disambiguation is presented as a case study.We begin by outlining the problem of ambiguous placenames. We demonstrate how analysis of Wikipedia can be used in the generation of a co-occurrence model. The accuracy of our model is compared to a handcrafted ground truth; then we evaluate alternative methods of applying this model to the disambiguation of placenames in free text (using the GeoCLEF evaluation forum). We conclude by showing how the inclusion of placenames in both the text and geographic parts of a query provides the maximum mean average precision and outline the benefits of a co-occurrence model as a data source for the wider field of geographic information retrieval (GIR).

In this paper we describe our Geographic Information Retrieval experiments with Forostar, our GIR application on the GeoCLEF 2007 corpus and query set. We compare the results from orthogonal text with no geographic entities and only geographic entities with standard text retrieval and combined text and geographic relevance methods. The text and named entity analysis and retrieval methods of Forostar are described in detail. We also detail our placename disambiguation and geographic relevance ranking methods. The paper concludes with an analysis of our results including significance testing where we show our baseline method, in fact, to be best. Finally we identify weaknesses in our approach and ways in which the system could be optimised and improved.

We detail our methods for generating and applying co-occurrence models for the purpose of placename disambiguation. We explain in detail our use of co-occurrence models for placename disambiguation using a model generated from Wikipedia. The presented system is split into two stages: a batch text & geographic indexer and a real time query engine. Four alternative query constructions and six methods of generating a geographic index are compared. The paper concludes with a full description of future work and ways in which the system could be optimised.

In this paper we describe the development of a geographic co-occurrence model and how it can be applied to geographic information retrieval. The model consists of mining co-occurrences of placenames from Wikipedia, and then mapping these placenames to locations in the Getty Thesaurus of Geographical Names. We begin by quantifying the accuracy of our model and compute theoretical bounds for the accuracy achievable when applied to placename disambiguation in free text. We conclude with a discussion of the improvement such a model could provide for placename disambiguation and geographic relevance ranking over traditional methods.

This year, ImageCLEF2007 data provided multiple evidences that can be explored in many different ways. In this paper we describe an i nformation retrieval framework that combines image, text and geographic data. Text analysis implements the vector space model based on non-geographic terms. Geographic analysis implements a placename disambiguation method and placenames are indexed by their Getty TGN Unique Id. Image analysis implements a query by semantic example model. The paper concludes with an analysis of our results. Fi nally we identify the weaknesses in our approach and ways in which the system could be optimised and improved.

image retrieval enables the user to search a database for visually similar images. In these scenarios, the user submits an example that is compared to the images in the database by their low-level characteristics such as colour, texture and shape. While visual similarity is essential for a vast number of applications, there are cases where a user needs to search for semantically similar images. For example, the user might want to find all images depicting bears on a river. This might be quite difficult using only low-level features, but using concept detectors for "bear" and "river" will produce results that are semantically closer to what the user requested. Following this idea, this paper studies a novel paradigm: query by semantic multimedia example. In this setting the user's query is processed at a semantic level: a vector of concept probabilities is inferred for each image and a similarity metric computes the distance between the concept vector of the query and of the concept vectors of the images in database. The system is evaluated with a COREL Stock Photo collection.