Biodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm

The natural world is very diverse in terms of biological organisation, and solves problems in a wide variety of efficient and creative manners. This biodiversity is in stark contrast with the landscape of artificial models in the field of Natural Language Processing (NLP). In the last years, NLP alg...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Simon Preissner, Aurélie Herbelot
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/6e3354bed5594003802a0f3d5a1ba80a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6e3354bed5594003802a0f3d5a1ba80a
record_format	dspace
spelling	oai:doaj.org-article:6e3354bed5594003802a0f3d5a1ba80a2021-12-02T09:52:31ZBiodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm2499-455310.4000/ijcol.609https://doaj.org/article/6e3354bed5594003802a0f3d5a1ba80a2020-06-01T00:00:00Zhttp://journals.openedition.org/ijcol/609https://doaj.org/toc/2499-4553The natural world is very diverse in terms of biological organisation, and solves problems in a wide variety of efficient and creative manners. This biodiversity is in stark contrast with the landscape of artificial models in the field of Natural Language Processing (NLP). In the last years, NLP algorithms have clustered around a few very expensive architectures, the cost of which has many facets, including training times, storage, replicability, interpretability, equality of access to experimental paradigms, and even environmental impact. Inspired by the biodiversity of the real world, we argue for a methodology which promotes ‘artificial diversity’, and we further propose that cognitively-inspired algorithms are a good starting point to explore new architectures. As a case study, we investigate the fruit fly’s olfactory system as a distributional semantics model. We show that, even in its rawest form, it provides many of the features that we might require from a good model of meaning acquisition, and that the original architecture can serve as a basis for cognitively-inspired extensions. We focus on one such extension by implementing a mechanism of neural adaptation.Simon PreissnerAurélie HerbelotAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 6, Iss 1, Pp 11-28 (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 Simon Preissner Aurélie Herbelot Biodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm
description	The natural world is very diverse in terms of biological organisation, and solves problems in a wide variety of efficient and creative manners. This biodiversity is in stark contrast with the landscape of artificial models in the field of Natural Language Processing (NLP). In the last years, NLP algorithms have clustered around a few very expensive architectures, the cost of which has many facets, including training times, storage, replicability, interpretability, equality of access to experimental paradigms, and even environmental impact. Inspired by the biodiversity of the real world, we argue for a methodology which promotes ‘artificial diversity’, and we further propose that cognitively-inspired algorithms are a good starting point to explore new architectures. As a case study, we investigate the fruit fly’s olfactory system as a distributional semantics model. We show that, even in its rawest form, it provides many of the features that we might require from a good model of meaning acquisition, and that the original architecture can serve as a basis for cognitively-inspired extensions. We focus on one such extension by implementing a mechanism of neural adaptation.
format	article
author	Simon Preissner Aurélie Herbelot
author_facet	Simon Preissner Aurélie Herbelot
author_sort	Simon Preissner
title	Biodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm
title_short	Biodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm
title_full	Biodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm
title_fullStr	Biodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm
title_full_unstemmed	Biodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm
title_sort	biodiversity in nlp: modelling lexical meaning with the fruit fly algorithm
publisher	Accademia University Press
publishDate	2020
url	https://doaj.org/article/6e3354bed5594003802a0f3d5a1ba80a
work_keys_str_mv	AT simonpreissner biodiversityinnlpmodellinglexicalmeaningwiththefruitflyalgorithm AT aurelieherbelot biodiversityinnlpmodellinglexicalmeaningwiththefruitflyalgorithm
_version_	1718397951051563008

Biodiversity in NLP: modelling lexical meaning with the Fruit Fly Algorithm

Ejemplares similares