Shanel  Reyes-Palacios

Ms. Shanel Reyes-Palacios

Body contour, American Society of Plastic Surgeons, Arlington Heights, Illinois, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 September 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
EAEdwyn Aldana-Bobadilla
Edwyn Aldana-Bobadilla
Alejandro Molina-VillegasAlejandro Molina-Villegas
Alejandro Molina-Villegas
ILIvan Lopez-Arevalo
Ivan Lopez-Arevalo
SRShanel Reyes-Palacios
Shanel Reyes-Palacios
VMVictor Muñiz-Sanchez
Victor Muñiz-Sanchez
JAJean Arreola
Jean Arreola
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).

4 November 2019 in Kalpa Publications in Computing
Verified
Conference Paper
Closed access
PDF file
SRShanel Reyes-Palacios
Shanel Reyes-Palacios
EAEdwin Aldana-Bobadilla
Edwin Aldana-Bobadilla
ILIvan Lopez-Arevalo
Ivan Lopez-Arevalo
Alejandro Molina-VillegasAlejandro Molina-Villegas
Alejandro Molina-Villegas
Modern Text Mining techniques seek for extract information in useful formats such as georeferences in digital documents. Automatic recognition of location names in texts is usually solved through Named Entity Recognition (NER) systems. Most current NER are based on Machine Learning and have very high accuracy in detection of location entities in digital documents, especially if the texts are in English due to the lack of available an- notated corpora in other languages. However, recent studies are dealing with the challenge of taking the output labels of a NER system and then gather, from a gazetteer, their exact unambiguous geographical coordinates. This is challenging mainly because toponyms use to be very ambiguous, so research in disambiguation methods is relevant. In this paper we describe some of the main ideas towards a method to associate locations with geographical data removing possible confusion between entities with the same name. So far, we have already accomplished Geographic NER and coordinates retrieval but the main research is still in course. We largely discuss about the state of the art around Geoparsing; we explain how our Geographic Entity Recognition module works and finally we describe the research proposal focusing in ambiguity detection.