Guardado en:
Detalles Bibliográficos
Autor principal: Ji, Eugene Yu
Formato: Preprint
Publicado: 2021
Materias:
Acceso en línea:https://arxiv.org/abs/2112.06876
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916707980804096
author Ji, Eugene Yu
author_facet Ji, Eugene Yu
contents In recent years, the field of NLP has seen growing interest in modeling both semantic and pragmatic dimensions. Despite this progress, two key challenges persist: firstly, the complex task of mapping and analyzing the interactions between semantic and pragmatic features; secondly, the insufficient incorporation of relevant insights from related disciplines outside NLP. Addressing these issues, this study introduces a novel geometric metric that utilizes word co-occurrence patterns. This metric maps two fundamental properties - semantic typicality (cognitive) and pragmatic salience (socio-cultural) - for basic-level categories within a two-dimensional hyperbolic space. Our evaluations reveal that this semantic-pragmatic metric produces mappings for basic-level categories that not only surpass traditional cognitive semantics benchmarks but also demonstrate significant socio-cultural relevance. This finding proposes that basic-level categories, traditionally viewed as semantics-driven cognitive constructs, should be examined through the lens of both semantic and pragmatic dimensions, highlighting their role as a cognitive-cultural interface. The broad contribution of this paper lies in the development of medium-sized, interpretable, and human-centric language embedding models, which can effectively blend semantic and pragmatic dimensions to elucidate both the cognitive and socio-cultural significance of linguistic categories.
format Preprint
id arxiv_https___arxiv_org_abs_2112_06876
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Cognitive and Cultural Topology of Linguistic Categories:A Semantic-Pragmatic Metric Approach
Ji, Eugene Yu
Computation and Language
In recent years, the field of NLP has seen growing interest in modeling both semantic and pragmatic dimensions. Despite this progress, two key challenges persist: firstly, the complex task of mapping and analyzing the interactions between semantic and pragmatic features; secondly, the insufficient incorporation of relevant insights from related disciplines outside NLP. Addressing these issues, this study introduces a novel geometric metric that utilizes word co-occurrence patterns. This metric maps two fundamental properties - semantic typicality (cognitive) and pragmatic salience (socio-cultural) - for basic-level categories within a two-dimensional hyperbolic space. Our evaluations reveal that this semantic-pragmatic metric produces mappings for basic-level categories that not only surpass traditional cognitive semantics benchmarks but also demonstrate significant socio-cultural relevance. This finding proposes that basic-level categories, traditionally viewed as semantics-driven cognitive constructs, should be examined through the lens of both semantic and pragmatic dimensions, highlighting their role as a cognitive-cultural interface. The broad contribution of this paper lies in the development of medium-sized, interpretable, and human-centric language embedding models, which can effectively blend semantic and pragmatic dimensions to elucidate both the cognitive and socio-cultural significance of linguistic categories.
title Cognitive and Cultural Topology of Linguistic Categories:A Semantic-Pragmatic Metric Approach
topic Computation and Language
url https://arxiv.org/abs/2112.06876