Home > Research > Publications & Outputs > Classifying encyclopedia articles

Links

Text available via DOI:

View graph of relations

Classifying encyclopedia articles: Comparing machine and deep learning methods and exploring their predictions

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Classifying encyclopedia articles: Comparing machine and deep learning methods and exploring their predictions. / Brenon, Alice; Moncla, Ludovic; Mcdonough, Katherine.
In: Data and Knowledge Engineering, Vol. 142, 102098, 30.11.2022.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Brenon A, Moncla L, Mcdonough K. Classifying encyclopedia articles: Comparing machine and deep learning methods and exploring their predictions. Data and Knowledge Engineering. 2022 Nov 30;142:102098. Epub 2022 Nov 14. doi: 10.1016/j.datak.2022.102098

Author

Bibtex

@article{e20e983d73d64fc287f59ae9c2fbfaee,
title = "Classifying encyclopedia articles: Comparing machine and deep learning methods and exploring their predictions",
abstract = "This article presents a comparative study of supervised classification approaches applied to the automatic classification of encyclopedia articles written in French. Our dataset is composed of 17 volumes of text from the Encyclop{\'e}die by Diderot and d'Alembert (1751-72) including about 70,000 articles. We combine text vectorization (bag-of-words and word embeddings) with machine learning methods, deep learning, and transformer architectures. In addition evaluating these approaches, we review the classification predictions using a variety of quantitative and qualitative methods. The best model obtains 86% as an average f-score for 38 classes. Using network analysis we highlight the difficulty of classifying semantically close classes. We also introduce examples of opportunities for qualitative evaluation of {"}misclassifications{"} in order to understand the relationship between content and different ways of ordering knowledge. We openly release all code and results obtained during this research.",
author = "Alice Brenon and Ludovic Moncla and Katherine Mcdonough",
year = "2022",
month = nov,
day = "30",
doi = "10.1016/j.datak.2022.102098",
language = "English",
volume = "142",
journal = "Data and Knowledge Engineering",
issn = "0169-023X",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Classifying encyclopedia articles

T2 - Comparing machine and deep learning methods and exploring their predictions

AU - Brenon, Alice

AU - Moncla, Ludovic

AU - Mcdonough, Katherine

PY - 2022/11/30

Y1 - 2022/11/30

N2 - This article presents a comparative study of supervised classification approaches applied to the automatic classification of encyclopedia articles written in French. Our dataset is composed of 17 volumes of text from the Encyclopédie by Diderot and d'Alembert (1751-72) including about 70,000 articles. We combine text vectorization (bag-of-words and word embeddings) with machine learning methods, deep learning, and transformer architectures. In addition evaluating these approaches, we review the classification predictions using a variety of quantitative and qualitative methods. The best model obtains 86% as an average f-score for 38 classes. Using network analysis we highlight the difficulty of classifying semantically close classes. We also introduce examples of opportunities for qualitative evaluation of "misclassifications" in order to understand the relationship between content and different ways of ordering knowledge. We openly release all code and results obtained during this research.

AB - This article presents a comparative study of supervised classification approaches applied to the automatic classification of encyclopedia articles written in French. Our dataset is composed of 17 volumes of text from the Encyclopédie by Diderot and d'Alembert (1751-72) including about 70,000 articles. We combine text vectorization (bag-of-words and word embeddings) with machine learning methods, deep learning, and transformer architectures. In addition evaluating these approaches, we review the classification predictions using a variety of quantitative and qualitative methods. The best model obtains 86% as an average f-score for 38 classes. Using network analysis we highlight the difficulty of classifying semantically close classes. We also introduce examples of opportunities for qualitative evaluation of "misclassifications" in order to understand the relationship between content and different ways of ordering knowledge. We openly release all code and results obtained during this research.

UR - https://hal.science/hal-03821073

U2 - 10.1016/j.datak.2022.102098

DO - 10.1016/j.datak.2022.102098

M3 - Journal article

VL - 142

JO - Data and Knowledge Engineering

JF - Data and Knowledge Engineering

SN - 0169-023X

M1 - 102098

ER -