Enregistré dans:
Détails bibliographiques
Auteurs principaux: Likhareva, Darya, Sankaran, Hamsini, Thiyagarajan, Sivakumar
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2404.13078
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910418194137088
author Likhareva, Darya
Sankaran, Hamsini
Thiyagarajan, Sivakumar
author_facet Likhareva, Darya
Sankaran, Hamsini
Thiyagarajan, Sivakumar
contents Researchers must stay current in their fields by regularly reviewing academic literature, a task complicated by the daily publication of thousands of papers. Traditional multi-label text classification methods often ignore semantic relationships and fail to address the inherent class imbalances. This paper introduces a novel approach using the SciBERT model and CNNs to systematically categorize academic abstracts from the Elsevier OA CC-BY corpus. We use a multi-segment input strategy that processes abstracts, body text, titles, and keywords obtained via BERT topic modeling through SciBERT. Here, the [CLS] token embeddings capture the contextual representation of each segment, concatenated and processed through a CNN. The CNN uses convolution and pooling to enhance feature extraction and reduce dimensionality, optimizing the data for classification. Additionally, we incorporate class weights based on label frequency to address the class imbalance, significantly improving the classification F1 score and enhancing text classification systems and literature review efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2404_13078
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Empowering Interdisciplinary Research with BERT-Based Models: An Approach Through SciBERT-CNN with Topic Modeling
Likhareva, Darya
Sankaran, Hamsini
Thiyagarajan, Sivakumar
Computation and Language
Machine Learning
Researchers must stay current in their fields by regularly reviewing academic literature, a task complicated by the daily publication of thousands of papers. Traditional multi-label text classification methods often ignore semantic relationships and fail to address the inherent class imbalances. This paper introduces a novel approach using the SciBERT model and CNNs to systematically categorize academic abstracts from the Elsevier OA CC-BY corpus. We use a multi-segment input strategy that processes abstracts, body text, titles, and keywords obtained via BERT topic modeling through SciBERT. Here, the [CLS] token embeddings capture the contextual representation of each segment, concatenated and processed through a CNN. The CNN uses convolution and pooling to enhance feature extraction and reduce dimensionality, optimizing the data for classification. Additionally, we incorporate class weights based on label frequency to address the class imbalance, significantly improving the classification F1 score and enhancing text classification systems and literature review efficiency.
title Empowering Interdisciplinary Research with BERT-Based Models: An Approach Through SciBERT-CNN with Topic Modeling
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2404.13078