Kate Byrne

Use of the Edinburgh geoparser for georeferencing digitized historical collections

We report on two JISC-funded projects that aimed to enrich the metadata of digitized historical collections with georeferences and other information automatically computed using geoparsing and related information extraction technologies. Understanding location is a critical part of any historical research, and the nature of the collections makes them an interesting case study for testing automated methodologies for extracting content. The two projects (GeoDigRef and Embedding GeoCrossWalk) have looked at how automatic georeferencing of resources might be useful in developing improved geographical search capacities across collections. In this paper, we describe the work that was undertaken to configure the geoparser for the collections as well as the evaluations that were performed.

Nested Named Entity Recognition in Historical Archive Text

This paper describes work on Named Entity Recognition (NER), in preparation for Relation Extraction (RE), on data from a historical archive organisation. As is often the case in the cultural heritage domain, the source text includes a high percentage of specialist terminology, and is of very variable quality in terms of grammaticality and completeness. The NER and RE tasks were carried out using a specially annotated corpus, and are themselves preliminary steps in a larger project whose aim is to transform discovered relations into a graph structure that can be queried using standard tools. Experimental results from the NER task are described, with emphasis on dealing with nested entities using a multi-word token method. The overall objective is to improve access by non-specialist users to a valuable cultural resource.

Evaluation of georeferencing

In this paper we describe a georeferencing system which first uses Information Extraction techniques to identify place names in textual documents and which then resolves the place names against a choice of gazetteers. We have used the system to georeference three digitised historical collections and have evaluated its performance against human annotated gold standard samples from the three collections. We have also evaluated its performance on the SpatialML corpus which is a geo-annotated corpus of newspaper text. The main focus of this paper is the evaluation of georesolution and we discuss evaluation methods and issues arising from the evaluation.

Adapting the Edinburgh Geoparser for Historical Georeferencing

Place name mentions in text may have more than one potential referent (e.g. Peru, the country vs. Peru, the city in Indiana). The Edinburgh Language Technology Group (LTG) has developed the Edinburgh Geoparser, a system that can automatically recognise place name mentions in text and disambiguate them with respect to a gazetteer. The recognition step is required to identify location mentions in a given piece of text. The subsequent disambiguation step, generally referred to as georesolution, grounds location mentions to their corresponding gazetteer entries with latitude and longitude values, for example, to visualise them on a map. Geoparsing is not only useful for mapping purposes but also for making document collections more accessible as it can provide additional metadata about the geographical content of documents. Combined with other information mined from text such as person names and date expressions, complex relations between such pieces of information can be identified. The Edinburgh Geoparser c...

GAP: A Neogeo Approach to Classical Resources

Google Ancient Places (GAP) is a Google Digital Humanities Award recipient that will mine the Google Books corpus for classical material that has a strong geographic and historical basis. GAP will allow scholars, students, and enthusiasts world-wide to query the Google Books corpus to ask for books related to a geographic location or to ask for the locations referred to in a classical text. The traditional difficulty of identifying place names will be overcome by using a combination of URI-based gazetteers and an identification algorithm that associates the linear clustering of places within narrative texts with the geographic clustering of locations in the real world.

A Web-based Geo-resolution Annotation and Evaluation Tool

In this paper we present the Edinburgh Geo-annotator, a web-based annotation tool for the manual geo-resolution of location mentions in text using a gazetteer. The annotation tool has an interlinked text and map interface which lets annotators pick correct candidates within the gazetteer more easily. The geo-annotator can be used to correct the output of a geoparser or to create gold standard geo-resolution data. We include accompanying scoring software for geo-resolution evaluation.

A Lightweight Treatment of Inexact Dates

This paper presents a lightweight approach to representing inexact dates on the semantic web, in that it imposes minimal ontological commitments on the ontology author and provides data that can be queried using standard approaches. The approach is presented in the context of a significant need to represent inexact dates but the heavyweight nature of existing proposals which can handle such information. Approaches to querying the represented information and an example user interface for creating such information are presented.