Guardado en:
Detalles Bibliográficos
Autores principales: Terreau, Enzo, Gourru, Antoine, Velcin, Julien
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2407.13358
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916811289657344
author Terreau, Enzo
Gourru, Antoine
Velcin, Julien
author_facet Terreau, Enzo
Gourru, Antoine
Velcin, Julien
contents A wide range of Deep Natural Language Processing (NLP) models integrates continuous and low dimensional representations of words and documents. Surprisingly, very few models study representation learning for authors. These representations can be used for many NLP tasks, such as author identification and classification, or in recommendation systems. A strong limitation of existing works is that they do not explicitly capture writing style, making them hardly applicable to literary data. We therefore propose a new architecture based on Variational Information Bottleneck (VIB) that learns embeddings for both authors and documents with a stylistic constraint. Our model fine-tunes a pre-trained document encoder. We stimulate the detection of writing style by adding predefined stylistic features making the representation axis interpretable with respect to writing style indicators. We evaluate our method on three datasets: a literary corpus extracted from the Gutenberg Project, the Blog Authorship Corpus and IMDb62, for which we show that it matches or outperforms strong/recent baselines in authorship attribution while capturing much more accurately the authors stylistic aspects.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13358
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Capturing Style in Author and Document Representation
Terreau, Enzo
Gourru, Antoine
Velcin, Julien
Computation and Language
Machine Learning
A wide range of Deep Natural Language Processing (NLP) models integrates continuous and low dimensional representations of words and documents. Surprisingly, very few models study representation learning for authors. These representations can be used for many NLP tasks, such as author identification and classification, or in recommendation systems. A strong limitation of existing works is that they do not explicitly capture writing style, making them hardly applicable to literary data. We therefore propose a new architecture based on Variational Information Bottleneck (VIB) that learns embeddings for both authors and documents with a stylistic constraint. Our model fine-tunes a pre-trained document encoder. We stimulate the detection of writing style by adding predefined stylistic features making the representation axis interpretable with respect to writing style indicators. We evaluate our method on three datasets: a literary corpus extracted from the Gutenberg Project, the Blog Authorship Corpus and IMDb62, for which we show that it matches or outperforms strong/recent baselines in authorship attribution while capturing much more accurately the authors stylistic aspects.
title Capturing Style in Author and Document Representation
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2407.13358