Analyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models

In recent years, there has been a significant increase in interest in lexical semantic change detection. Many are the existing approaches, data used, and evaluation strategies to detect semantic shifts. The classification of change words against stable words requires thresholds to label the degree o...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pierluigi Cassotti, Pierpaolo Basile, Marco de Gemmis, Giovanni Semeraro
Formato:	article
Lenguaje:	EN
Publicado:	Accademia University Press 2020
Materias:	Social Sciences H Computational linguistics. Natural language processing P98-98.5
Acceso en línea:	https://doaj.org/article/a14bafd2a2e6422bb8ec7fb664f36ebe
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a14bafd2a2e6422bb8ec7fb664f36ebe
record_format	dspace
spelling	oai:doaj.org-article:a14bafd2a2e6422bb8ec7fb664f36ebe2021-12-02T09:52:35ZAnalyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models2499-455310.4000/ijcol.714https://doaj.org/article/a14bafd2a2e6422bb8ec7fb664f36ebe2020-12-01T00:00:00Zhttp://journals.openedition.org/ijcol/714https://doaj.org/toc/2499-4553In recent years, there has been a significant increase in interest in lexical semantic change detection. Many are the existing approaches, data used, and evaluation strategies to detect semantic shifts. The classification of change words against stable words requires thresholds to label the degree of semantic change. In this work, we compare state-of-the-art computational historical linguistics approaches to evaluate the efficacy of thresholds based on the Gaussian Distribution of semantic shifts. We present the results of an in-depth analysis conducted on both SemEval-2020 Task 1 Subtask 1 and DIACR-Ita tasks. Specifically, we compare Temporal Random Indexing, Temporal Referencing, Orthogonal Procrustes Alignment, Dynamic Word Embeddings and Temporal Word Embedding with a Compass. While results obtained with Gaussian thresholds achieve state-of-the-art performance in English, German, Swedish and Italian, they remain far from results obtained using the optimal threshold.Pierluigi CassottiPierpaolo BasileMarco de GemmisGiovanni SemeraroAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 6, Iss 2, Pp 23-36 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Social Sciences H Computational linguistics. Natural language processing P98-98.5
spellingShingle	Social Sciences H Computational linguistics. Natural language processing P98-98.5 Pierluigi Cassotti Pierpaolo Basile Marco de Gemmis Giovanni Semeraro Analyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models
description	In recent years, there has been a significant increase in interest in lexical semantic change detection. Many are the existing approaches, data used, and evaluation strategies to detect semantic shifts. The classification of change words against stable words requires thresholds to label the degree of semantic change. In this work, we compare state-of-the-art computational historical linguistics approaches to evaluate the efficacy of thresholds based on the Gaussian Distribution of semantic shifts. We present the results of an in-depth analysis conducted on both SemEval-2020 Task 1 Subtask 1 and DIACR-Ita tasks. Specifically, we compare Temporal Random Indexing, Temporal Referencing, Orthogonal Procrustes Alignment, Dynamic Word Embeddings and Temporal Word Embedding with a Compass. While results obtained with Gaussian thresholds achieve state-of-the-art performance in English, German, Swedish and Italian, they remain far from results obtained using the optimal threshold.
format	article
author	Pierluigi Cassotti Pierpaolo Basile Marco de Gemmis Giovanni Semeraro
author_facet	Pierluigi Cassotti Pierpaolo Basile Marco de Gemmis Giovanni Semeraro
author_sort	Pierluigi Cassotti
title	Analyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models
title_short	Analyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models
title_full	Analyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models
title_fullStr	Analyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models
title_full_unstemmed	Analyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models
title_sort	analyzing gaussian distribution of semantic shifts in lexical semantic change models
publisher	Accademia University Press
publishDate	2020
url	https://doaj.org/article/a14bafd2a2e6422bb8ec7fb664f36ebe
work_keys_str_mv	AT pierluigicassotti analyzinggaussiandistributionofsemanticshiftsinlexicalsemanticchangemodels AT pierpaolobasile analyzinggaussiandistributionofsemanticshiftsinlexicalsemanticchangemodels AT marcodegemmis analyzinggaussiandistributionofsemanticshiftsinlexicalsemanticchangemodels AT giovannisemeraro analyzinggaussiandistributionofsemanticshiftsinlexicalsemanticchangemodels
_version_	1718397959747403776

Analyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models

Ejemplares similares