Adaptive Geoparsing Method for Toponym Recognition and Resolution in Unstructured Text

Abstract

The automatic extraction of geospatial information is an important aspect of data mining. Computer systems capable of discovering geographic information from natural language involve a complex process called geoparsing, which includes two important tasks: geographic entity recognition and toponym resolution. The first task could be approached through a machine learning approach, in which case a model is trained to recognize a sequence of characters (words) corresponding to geographic entities. The second task consists of assigning such entities to their most likely coordinates. Frequently, the latter process involves solving referential ambiguities. In this paper, we propose an extensible geoparsing approach including geographic entity recognition based on a neural network model and disambiguation based on what we have called dynamic context disambiguation. Once place names are recognized in an input text, they are solved using a grammar, in which a set of rules specifies how ambiguities could be solved, in a similar way to that which a person would utilize, considering the context. As a result, we have an assignment of the most likely geographic properties of the recognized places. We propose an assessment measure based on a ranking of closeness relative to the predicted and actual locations of a place name. Regarding this measure, our method outperforms OpenStreetMap Nominatim. We include other assessment measures to assess the recognition ability of place names and the prediction of what we called geographic levels (administrative jurisdiction of places).

Rapid Production Method of Massive Thematic Maps Based on Geospatial Knowledge Extraction

“…This method is consistent with the idea of understanding spatio-temporal semantics in texts, and has become the mainstream method in the field of place name disambiguation at home and abroad. The heuristic rule approach mainly uses maps [8] , external resources [9] , semantics [10] , cognitive salience [11] , a library of conceptual relationships of place names [12] and geographic relatedness [13] to construct rules that are used to inspire contextual semantics, so as to determine the unique linguistic meaning for the referred place names and thus perform place name disambiguation. Although constructing rules from different perspectives can eliminate the ambiguity of geographical names to a certain extent, it has the limitation that each rule is highly targeted and the focus of disambiguation is poorly correlated in scope.…”

SNEToolkit: Spatial named entities disambiguation toolkit

“…In the literature, we can distinguish four main approaches for spatial named entity disambiguation. (i) Approaches based on rules and criteria, such as the Geonames 5 database, for native disambiguation that uses geographic level and population size. In [2], the authors include a similarity measure of the basics rules of Geonames by using the Levenshtein distance measure to compute the similarity between the extracted place name in the text and the others proposed by the Geonames database.…”

“…The authors in [3] also applied fuzzy logic techniques to resolve spatial ambiguities. Some approaches, such as [4], use knowledge graphs or gazetteers [5] to disambiguate named entities. (ii) The second approach uses Machine Learning methods [6] to disambiguate spatial named entities within the textual data.…”

A Deep Transfer Learning Toponym Extraction and Geospatial Clustering Framework for Investigating Scenic Spots as Cognitive Regions

“…Artificial neural networks are an effective method to address the issues of generality and scalability. When the amount of data is small, applying a simple neural network structure to extract toponyms from unstructured textual data is an effective approach [22][23][24][25]. However, simple neural network structures may have issues of underfitting when applied to large-scale corpora.…”