Cargando...
Fecha
2022-12-01
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editorial
Massachusetts Institute of Technology Press
Citas
0 citas en 
0 citas en 
Resumen
In the context of text representation, Compositional Distributional Semantics models aim to fuse the Distributional Hypothesis and the Principle of Compositionality. Text embedding is based on co-ocurrence distributions and the representations are in turn combined by compositional functions taking into account the text structure. However, the theoretical basis of compositional functions is still an open issue. In this article we define and study the notion of Information Theory–based Compositional Distributional Semantics (ICDS): (i) We first establish formal properties for embedding, composition, and similarity functions based on Shannon’s Information Theory; (ii) we analyze the existing approaches under this prism, checking whether or not they comply with the established desirable properties; (iii) we propose two parameterizable composition and similarity functions that generalize traditional approaches while fulfilling the formal properties; and finally (iv) we perform an empirical study on several textual similarity datasets that include sentences with a high and low lexical overlap, and on the similarity between words and their description. Our theoretical analysis and empirical results show that fulfilling formal properties affects positively the accuracy of text representation models in terms of correspondence (isometry) between the embedding and meaning spaces.
Descripción
The registered version of this article, first published in “Computational Linguistics 2022; 48 (4): 907–948", is available online at the publisher's website: Massachusetts Institute of Technology Press, https://doi.org/10.1162/coli_a_00454
La versión registrada de este artículo, publicado por primera vez en “Computational Linguistics 2022; 48 (4): 907–948", está disponible en línea en el sitio web del editor: Massachusetts Institute of Technology Press, https://doi.org/10.1162/coli_a_00454
La versión registrada de este artículo, publicado por primera vez en “Computational Linguistics 2022; 48 (4): 907–948", está disponible en línea en el sitio web del editor: Massachusetts Institute of Technology Press, https://doi.org/10.1162/coli_a_00454
Categorías UNESCO
Palabras clave
Citación
Enrique Amigó, Alejandro Ariza-Casabona, Victor Fresno, M. Antònia Martí (2022); Information Theory–based Compositional Distributional Semantics. Computational Linguistics; 48 (4): 907–948. doi: https://doi.org/10.1162/coli_a_00454
Centro
E.T.S. de Ingeniería Informática
Departamento
Lenguajes y Sistemas Informáticos