A Comparison of Approaches for Geospatial Entity Extraction from Wikipedia

Woodward, Daryl; Witmer, Jeremy; Kalita, Jugal

doi:10.1109/icsc.2010.74

Cited by 8 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Word2vec's dimension is 300. Hidden Markov Model (HMM) [21], CRF [23], IDCNN-CRF [29] and BLSTM-CRF [30] are used as baseline models of BERT-WWM+BLSTM-CRF urban data recognition model.…”

Section: Results and Analysis 1) Comparative Experiments Of Urban Dmentioning

confidence: 99%

“…The selection of data source and the construction of data extraction model are two key issues. Most of the work for extracting urban data from Internet resources (e.g., [12], [21]) usually sets one or more specific websites as the stable data source. However, the use of specific websites as data sources limits the diversity of data collection, making it difficult to obtain data with available comprehensiveness.…”

Section: Data Extraction and Web Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

SUDIR: An Approach of Sensing Urban Text Data From Internet Resources Based on Deep Learning

2020

View full text Add to dashboard Cite

Urban data is a imperative resource for urban computing, which can promote the establishment of urban knowledge, the collection of urban information and the construction of smart cities. Seen that the urban data collected through hardware sensors and crowdsourcing has the limitations of uneven information distribution, poor data comprehensiveness and high resource costs, we turn to the Internet resources of real-time updates and extensive information coverage. Therefore, we propose an approach to Sensing Urban text Data from Internet Resources (SUDIR). We put forward innovative work on two key issues: urban data recognition for Chinese context and urban data sensing for multi-source web resources. On one hand, we design a Chinese urban data recognition model based on Whole Word Masking for Bidirectional Encoder Representations from Transformers (BERT-WWM) embedding model and Bidirectional Long-Short Term Memory with a Conditional Random Field (BLSTM-CRF) sequence labeling model. We introduce Chinese Word Segmentaion (CWS) concept in BERT embedding model to make the text embedding effect better represent semantic information on Chinese context. BLSTM-CRF model based on deep learning is used to achieve high-quality coding and prediction. On the other hand, we propose a method of Extracting Urban text data based on Web page features and Clustering operation (EUWC). EUWC is used to correct the false negative samples labeled by BERT-WWM+BLSTM-CRF recognition model and enable SUDIR to sense more accurate and comprehensive city data from multisource web resources. The experimental results show that our work outperforms the other baseline methods, and it also proves that SUDIR using Internet resources and deep learning technology has the advantages of low-cost, high-quality urban data sensing.

show abstract

“…Word2vec's dimension is 300. Hidden Markov Model (HMM) [21], CRF [23], IDCNN-CRF [29] and BLSTM-CRF [30] are used as baseline models of BERT-WWM+BLSTM-CRF urban data recognition model.…”

Section: Results and Analysis 1) Comparative Experiments Of Urban Dmentioning

confidence: 99%

Section: Data Extraction and Web Clusteringmentioning

confidence: 99%

SUDIR: An Approach of Sensing Urban Text Data From Internet Resources Based on Deep Learning

2020

View full text Add to dashboard Cite

show abstract

“…Our goal was to see if an especially trained and tuned SVM will perform better than HMM or CRF approaches, particularly for geospatial names. More details can be found in [76,75,77,91].…”

Section: Experiments In Geospatial Named Entity Extractionmentioning

confidence: 99%

Extracting and Displaying Temporal and Geospatial Entities from Articles on Historical Events

Chasin¹,

Woodward²,

Witmer³

et al. 2013

The Computer Journal

View full text Add to dashboard Cite

This paper discusses a system that extracts and displays temporal and geospatial entities in text. The first task involves identification of all events in a document followed by identification of important events using a classifier. The second task involves identifying named entities associated with the document. In particular, we extract geospatial named entities. We disambiguate the set of geospatial named entities and geocode them to determine the correct coordinates for each place name, often called grounding. We resolve ambiguity based on sentence and article context. Finally, we present a user with the key events and their associated people, places, and organizations within a document in terms of a timeline and a map. For purposes of testing, we use Wikipedia articles about historical events, such as those describing wars, battles, and invasions. We focus on extracting major events from the articles, although our ideas and tools can be easily used with articles from other sources such as news articles. We use several existing tools such as Evita, Google Maps, publicly available implementations of SVM, HMM and CRF, and the MIT SIMILE Timeline.

show abstract

“…This research is complemented by work on place name entity recognition and extraction [5,15] and more recent efforts to extend geoparsing methods to microblog and other more cryptic social media posts [3]. Nowadays a number of geoparsers and related software tools and services exist for identifying and geolocating places in different types of unstructured text ( [4], see also [2] for a more exhaustive list), and in microblog or Twitter messages in particular [3,7].…”

Section: Introductionmentioning

confidence: 99%

Construction and first analysis of a corpus for the evaluation and training of microblog/twitter geoparsers

Wallgrün

Hardisty

MacEachren

et al. 2014

Proceedings of the 8th Workshop on Geographic Information Retrieval

View full text Add to dashboard Cite

This article presents an approach to place reference corpus building and application of the approach to a Geo-Microblog Corpus that will foster research and development in the areas of microblog/twitter geoparsing and geographic information retrieval. Our corpus currently consists of 6000 tweets with identified and georeferenced place names. 30% of the tweets contain at least one place name. The corpus is intended to support the evaluation, comparison, and training of geoparsers. We introduce our corpus building framework, which is developed to be generally applicable beyond microblogs, and explain how we use crowdsourcing and geovisual analytics technology to support the construction of relatively large corpora. We then report on the corpus building work and present an analysis of causes of disagreement between the lay persons performing place identification in our crowdsourcing approach.

show abstract

A Comparison of Approaches for Geospatial Entity Extraction from Wikipedia

Cited by 8 publications

References 10 publications

SUDIR: An Approach of Sensing Urban Text Data From Internet Resources Based on Deep Learning

SUDIR: An Approach of Sensing Urban Text Data From Internet Resources Based on Deep Learning

Extracting and Displaying Temporal and Geospatial Entities from Articles on Historical Events

Construction and first analysis of a corpus for the evaluation and training of microblog/twitter geoparsers

Contact Info

Product

Resources

About