Skip to Main content Skip to Navigation
Theses

Deteccion y extraccion de neologismos semanticos especializados : un acercamiento mediante clasificacion automatica de documentos y estrategias de aprendieaje profundo

Abstract : In the field of neology, different methodological approaches for the detection and extractionof semantic neologisms have been developed using strategies such as word sensedisambiguation and topic modeling, but there is still not a proposal for a system for thedetection of these units. Beginning from a detailed study on the necessary theoreticalassumptions required to delimit and describe semantic neologisms, in this thesis, we proposethe development of an application to identify and extract said units using statistical,data mining and machine learning strategies. The proposed methodology is based ontreating the process of detection and extraction as a classification task, which consists onanalyzing the concordance of topics between the semantic field from the main meaningof a word and the text where it is found. To build the architecture of the proposed system,we analyzed five automatic classification methods and three deep learning based wordembedding models. Our analysis corpus is composed of the semantic neologisms of thecomputer science field belonging to the database of the Observatory of Neology of thePompeu Fabra University, which have been registered from 1989 to 2015. We used thiscorpus to evaluate the different methods that our system implements: automatic classification,keyword extraction from short contexts, and similarity list generation. This firstmethodological approach aims to establish a framework of reference in terms of detectionand extraction of semantic neologisms.
Document type :
Theses
Complete list of metadatas

Cited literature [280 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02524841
Contributor : Abes Star :  Contact
Submitted on : Monday, March 30, 2020 - 3:44:13 PM
Last modification on : Thursday, July 2, 2020 - 11:56:36 AM

File

these_andres_torres.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02524841, version 1

Collections

Citation

Andrés Torres Rivera. Deteccion y extraccion de neologismos semanticos especializados : un acercamiento mediante clasificacion automatica de documentos y estrategias de aprendieaje profundo. Technology for Human Learning. Université d'Avignon; Universitat Pompeu Fabra (Barcelone, Espagne), 2019. Español. ⟨NNT : 2019AVIG0232⟩. ⟨tel-02524841⟩

Share

Metrics

Record views

93

Files downloads

385