Recent developments in the field of artificial intelligence has led to renewed interest in natural language processing. Named entity recognition (NER) is a classic problem in natural language ...processing. Investigating named entities is a continuing concern within information extraction. Names of people, organizations, locations, events, etc. are named entities (NEs). Although extensive research has been carried out on NER, limited study exists that explores NER in the Marathi language. The paper aims to provide a conceptual theoretical framework based on the gazetteer matching technique for named entity recognition system development for the Marathi language. A combination of rules and regular expressions is considered for temporal and numerical pattern recognition. The techniques presented in this paper are systematic, clear, and effective for morphologically rich language processing tool development. The system described in the paper reports a satisfactory performance with 62.64% NE identification and 72.27% NE classification accuracy.
The advent of desktop GIS systems, along with increasing access to high-speed internet connections in the academy, has led to what some call the "spatial turn" in the study of history, and more ...broadly, the humanities. The Pleiades and World Historical Gazetteer (WHG) projects represent the intersection of spatial theory and digital methodologies, a unique combination that situates them at the forefront of spatial history. Both projects began with the digitization of an exemplar print gazetteer, and have grown to embrace a collaborative model of research and development. In addition to producing and consuming geospatial content, both projects are heavily involved in the theorization and reconceptualization of such fundamental ideas as place, space, and the expression of relationships between geographic and political entities. This article outlines theoretical and methodological approaches of the two projects and highlights the increasing use and importance of linked data in the practice of digital spatial history. It explores how a wide variety of projects can leverage resources like Pleiades and the WHG, which allows for the development of new research while simultaneously contributing to the growing spatial history digital ecosystem.
The “Mesopotamian Ancient Place-names Almanac” (MAPA) focuses on the southern Mesopotamian city of Uruk and its extensive hinterland (Biblical Erech, modern Warka), one of the world’s first ...mega-cities. Uruk possesses some of the earliest attestations of the cuneiform writing system, and boasts of being the royal seat of the legendary king Gilgamesh. MAPA is a first step in integrating textual sources with remote sensing data for reconstructing the social and physical geography of Mesopotamia in the Age of Empires. The dataset presented here is the recent edition of the gazetteer (v1.0) follows linked open data (LOD) protocols, and draws close to 400 placenames from legal, economic, and administrative texts mostly from the first millennium BCE rich archives of Uruk; namely, those produced under the Assyrian, Babylonian and Achaemenid empires.
•A data-driven approach to construct gazetteers from volunteered geographic information was introduced.•We built a high-performance Hadoop-based geoprocessing platform to facilitate gazetteer ...research.•It connects spatial analysis to the cloud computing environment for Big Geo-Data analytics.
Traditional gazetteers are built and maintained by authoritative mapping agencies. In the age of Big Data, it is possible to construct gazetteers in a data-driven approach by mining rich volunteered geographic information (VGI) from the Web. In this research, we build a scalable distributed platform and a high-performance geoprocessing workflow based on the Hadoop ecosystem to harvest crowd-sourced gazetteer entries. Using experiments based on geotagged datasets in Flickr, we find that the MapReduce-based workflow running on the spatially enabled Hadoop cluster can reduce the processing time compared with traditional desktop-based operations by an order of magnitude. We demonstrate how to use such a novel spatial-computing infrastructure to facilitate gazetteer research. In addition, we introduce a provenance-based trust model for quality assurance. This work offers new insights on enriching future gazetteers with the use of Hadoop clusters, and makes contributions in connecting GIS to the cloud computing environment for the next frontier of Big Geo-Data analytics.
The region of the Luofu Mountains in Guangdong, China, has long been a Daoist sacred place for centuries. In the Daoist sacred geographic system “Dongtian Fudi” (Grotto-Heavens and Blissful Lands), ...the Luofu Mountains are ranked as the seventh “Major Grotto-Heaven”, standing as an influential site for the practice Daoist immortals. Due to a sense of local pride and responsibility, the Guangdong literatus Han Huang (active approx. 1600–1639) compiled an important gazetteer named Luofu yesheng (The Unofficial Gazetteer of the Luofu Mountains) in 1639, which is largely underexplored. By investigating the texts and images within Luofu yesheng and by comparing them with other gazetteers of the Luofu Mountains compiled during the Ming dynasty, this article discovers that Han Huang compiled such a gazetteer and demonstrated the religious sacredness of the Luofu Mountains to advocate for recognition of their status as a grotto-heaven and by imaginatively reconstructing their lost religious sites in Luofu yesheng’s texts and images.
Well before the innovation of maps, gazetteers served as the main geographic referencing system for hundreds of years. Consisting of a specialized index of place names, gazetteers traditionally ...linked descriptive elements with topographic features and coordinates. Placing Names is inspired by that tradition of discursive place-making and by contemporary approaches to digital data management that have revived the gazetteer and guided its development in recent decades. Adopted by researchers in the Digital Humanities and Spatial Sciences, gazetteers provide a way to model the kind of complex cultural, vernacular, and perspectival ideas of place that can be located in texts and expanded into an interconnected framework of naming history. This volume brings together leading and emergent scholars to examine the history of the gazetteer, its important role in geographic information science, and its use to further the reach and impact of spatial reasoning into the digital age.
Trail of Footprints offers an intimate glimpse into the commission, circulation, and use of indigenous maps from colonial Mexico. A collection of sixty largely unpublished maps from the late ...sixteenth to the eighteenth centuries and made in the southern region of Oaxaca anchors an analysis of the way ethnically diverse societies produced knowledge in colonial settings. Mapmaking, proposes Hidalgo, formed part of an epistemological shift tied to the negotiation of land and natural resources between the region’s Spanish, Indian, and mixed-race communities. The craft of making maps drew from social memory, indigenous and European conceptions of space and ritual, and Spanish legal practices designed to adjust spatial boundaries in the New World. Indigenous mapmaking brought together a distinct coalition of social actors—Indian leaders, native towns, notaries, surveyors, judges, artisans, merchants, muleteers, collectors, and painters—who participated in the critical observation of the region’s geographic features. Demand for maps reconfigured technologies associated with the making of colorants, adhesives, and paper that drew from Indian botany and experimentation, trans-Atlantic commerce, and Iberian notarial culture. The maps in this study reflect a regional perspective associated with Oaxaca’s decentralized organization, its strategic position amidst a network of important trade routes that linked central Mexico to Central America, and the ruggedness and diversity of its physical landscape.
PDF
