Toponym matching through deep neural networks

Santos, Rui; Murrieta-Flores, Patricia; Calado, Pável; Martins, Bruno

doi:10.1080/13658816.2017.1390119

Cited by 63 publications

(72 citation statements)

References 47 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently ongoing efforts focus on extending the method advanced in this paper in two different directions, namely (i) improving Step 2 with a new string matching method, leveraging a deep neural network architecture for modeling the strings being compared [28], and (ii) improving Step 3 with a novel approach for computing least-cost paths between consecutive locations in the itineraries, leveraging raster datasets encoding terrain slope and/or historical land-coverage [3,8,23]. Table 2.…”

Section: Discussionmentioning

confidence: 99%

“…referring to different regions of the globe, and/or using other types of toponyms (e.g., involving different alphabets, and different challenges in terms of performing matches against gazetteer entries [28]). A particular example would be the dataset from the al-Thurayyā Gazetteer 8 , which includes almost 2,000 route sections geo-referenced from Georgette Cornu's atlas du monde arabo-islamique à l'époque classique: IXe-Xe siècles.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

An Automated Approach for Geocoding Tabular Itineraries

Santos

Murrieta-Flores

Martins

2017

Proceedings of the 11th Workshop on Geographic Information Retrieval

Self Cite

View full text Add to dashboard Cite

Historical itineraries, often accessible as lists or tables describing places visited in sequence, are abundant resources and also important objects of study for humanities scholars. This article advances a novel method for automatically geocoding tabular itineraries, combining approximate string matching with a cost optimization algorithm based on dynamic programming. Experiments with a dataset of historical itineraries, with ground-truth geocoding annotations provided by domain experts and leveraging also the GeoNames gazetteer, attest to the effectiveness of the proposed method. The obtained results show that while approximate string matching can already achieve very low median errors, with many toponyms matching exactly against GeoNames entries, the combination with cost optimization can significantly improve results in terms of the average distance towards the correct disambiguations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

An Automated Approach for Geocoding Tabular Itineraries

Santos

Murrieta-Flores

Martins

2017

Proceedings of the 11th Workshop on Geographic Information Retrieval

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep Learning methods for toponym interlinking are also being proposed in the literature. [13] present such a method, were Siamese RNNs are applied, yielding better accuracy results than traditional classifiers on similarity-based training features. Incorporating Deep Learning methods eliminates the need for feature extraction and engineering, however, it requires large amounts of data to train proper models, as well as engineering proper DNN architectures.…”

Section: Related Workmentioning

confidence: 99%

“…Comparing traditional classification methods with Deep Learning methods, as well as devising approaches for exploiting both worlds comprises part of our ongoing work. Thus, in the current manuscript, the approach of [13] is considered orthogonal but potentially complementary.…”

Section: Related Workmentioning

confidence: 99%

Learning Advanced Similarities and Training Features for Toponym Interlinking

Giannopoulos

Kaffes

Kostoulas

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Interlinking of spatio-textual entities is an open and quite challenging research problem, with application in several commercial fields, including geomarketing, navigation and social networks. It comprises the process of identifying, between different data sources, entity descriptions that refer to the same real-world entity. In this work, we focus on toponym interlinking, that is we handle spatio-textual entities that are exclusively represented by their name; additional properties, such as categories, coordinates, etc. are considered as either absent or of too low quality to be exploited in this setting. Toponyms are inherently heterogeneous entities; quite often several alternative names exist for the same toponym, with varying degrees of similarity between these names. State of the art approaches adopt mostly generic, domain-agnostic similarity functions and use them as is, or incorporate them as training features within classifiers for performing toponym interlinking. We claim that capturing the specificities of toponyms and exploiting them into elaborate meta-similarity functions and derived training features can significantly increase the effectiveness of interlinking methods. To this end, we propose the LGM-Sim meta-similarity function and a series of novel, similarity-based and statistical training features that can be utilized in similarity-based and classification-based interlinking settings respectively. We demonstrate that the proposed methods achieve large increases in accuracy, in both settings, compared to several methods from the literature in the widely used Geonames toponym dataset.

show abstract

“…RNNs, such as Long Short-Term Memory (LSTM), are utilized to handle time series data, such as predicting the next locations of trajectories ) and examining the temporal patterns of crops (Sun et al 2018). RNNs are also used for analyzing geotagged tweets and other natural language texts containing geographic information (Mao et al 2018b, Sit et al 2019, Santos et al 2018. Machine learning models, such as hidden Markov model, are integrated with a variety of geospatial applications, such as indoor navigation (Li et al 2017a) and location prediction of financial services (McKenzie and Slind 2019).…”

Section: Summary and Some Other Applications Of Ai In Geographymentioning

confidence: 99%

Artificial Intelligence Approaches

Wright

et al. 2019

GIS&T BoK

View full text Add to dashboard Cite

Artificial Intelligence (AI) has received tremendous attention from academia, industry, and the general public in recent years. The integration of geography and AI, or GeoAI, provides novel approaches for addressing a variety of problems in the natural environment and our human society. This entry briefly reviews the recent development of AI with a focus on machine learning and deep learning approaches. We discuss the integration of AI with geography and particularly geographic information science, and present a number of GeoAI applications and possible future directions. Definitions Artificial Intelligence:The study and design of machines or computational methods that can perform tasks that normally require human intelligence. 2. GeoAI: An interdisciplinary field of geography and artificial intelligence. Machine Learning:A sub field in AI that relies on statistical methods or numerical optimization techniques to derive models from data without explicitly programming every model parameter or computing step. Deep Learning:A special type of machine learning that leverages multiple layers of nonlinear processing units, or neurons, to learn representations from raw data to achieve the goal of automatic learning for completing various AI tasks.Description/body AI and GeographyArtificial Intelligence (AI) has received tremendous attention in recent years from academia, industry, and the general public. Despite its recent popularity, the field was born back in 1956 at a workshop at Dartmouth College (McCarthy 1956). AI is a broad field from its beginning, and has many different definitions (Russell et al. 2003). Some definitions focus on designing intelligent machines that can act like humans. For example, the famous Turing Test was designed to see if the responses of a machine can be indistinguishable from those of a real person (Turing 1950). Some other definitions focus on designing and developing computational methods to complete tasks that typically require human intelligence, such as recognizing objects from images or understanding the meaning of natural language sentences. This entry is primarily based on the second type of definitions.The development of AI has experienced falls and rises. Following its early optimism in 1960s and 70s, AI research went through the "AI winter" due to the failures of AI methods in addressing real-world problems. The following decades witnessed several other waves of optimism and disappointment. Since the 21th century, and especially after 2010, there has been significant progress in AI research. Three major factors have contributed to this fast advancement of AI: big data, novel algorithms, and immense computational power. The emergence of ubiquitous sensors and user-generated content on the Web

show abstract

Toponym matching through deep neural networks

Cited by 63 publications

References 47 publications

An Automated Approach for Geocoding Tabular Itineraries

An Automated Approach for Geocoding Tabular Itineraries

Learning Advanced Similarities and Training Features for Toponym Interlinking

Artificial Intelligence Approaches

Contact Info

Product

Resources

About