We take great pleasure in welcoming you to the twelfth workshop on Geographic Information Retrieval (GIR'18). The workshops have been running since 2004 and after being hosted previously by ACM SIGIR and ACM CIKM are now firmly established in their relationship with ACM SIGSPATIAL. Alternating the event between the ACM SIGSPATIAL conference in the USA and a stand-alone event in Europe has proved successful in enabling us to attract a varied audience to the workshop. There has also been a difference in duration, with two day meetings in Europe (previously in Zurich, Paris and Heidelberg) allowing us more time for discussion and an associated social programme.
Proceeding Downloads
From spatial representation to processes, relational networks, and thematic roles in geographic information retrieval
Geographic information retrieval (GIR) has largely been synonymous with spatial information retrieval. However, geographic information in text is not always explicitly, nor even implicitly, spatial, and when people are seeking geographic information, it ...
Automatically creating a spatially referenced corpus of landscape perception
Spatially referenced thematically relevant corpora are an important first step in analyzing a wide variety of phenomena. Here, we describe and evaluate a workflow which extracts descriptions containing first person perception of landscape, and ...
EUPEG: Towards an Extensible and Unified Platform for Evaluating Geoparsers
Geoparsing, namely recognizing and geo-locating place mentions from unstructured texts, is a critical task in geographic information retrieval (GIR). While a number of geoparsers have been developed, they were often tested on different datasets using ...
Machine Learning to Improve Retrieval by Category in Big Volunteered Geodata
Nowadays, Volunteered Geographic Information (VGI) is commonly used in research and practical applications. However, the quality assurance of such a geographic data remains a problem. In this study we use machine learning and natural language processing ...
POIReviewQA: A Semantically Enriched POI Retrieval and Question Answering Dataset
Many services that perform information retrieval for Points of Interest (POI) utilize a Lucene-based setup with spatial filtering. While this type of system is easy to implement it does not make use of semantics but relies on direct word matches between ...
Evaluating the Representativeness in the Geographic Distribution of Twitter User Population
Twitter data are becoming a Big Data stream and have drawn multidisciplinary interests to study population characteristics and social problems that cannot be measured well by traditional surveys. However, the use of Twitter data has been strongly ...
Template-Based Question Answering over Linked Geospatial Data
- D. Punjani,
- K. Singh,
- A. Both,
- M. Koubarakis,
- I. Angelidis,
- K. Bereta,
- T. Beris,
- D. Bilidas,
- T. Ioannidis,
- N. Karalis,
- C. Lange,
- D. Pantazi,
- C. Papaloukas,
- G. Stamoulis
Large amounts of geospatial data have been made available recently on the linked open data cloud and on the portals of many national cartographic agencies (e.g., OpenStreetMap data, administrative geographies of various countries, or land cover/land use ...
Towards Generalizable Place Name Recognition Systems: Analysis and Enhancement of NER Systems on English News from India
Place name recognition is one of the key tasks in Information Extraction. In this paper, we tackle this task in English News from India. We first analyze the results obtained by using available tools and corpora and then train our own models to obtain ...
Index Terms
- Proceedings of the 12th Workshop on Geographic Information Retrieval