Enriching language models with graph-based context information to better understand textual data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Roethel, Albert, Ganzha, Maria, Wróblewska, Anna
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916884421541888
author Roethel, Albert
Ganzha, Maria
Wróblewska, Anna
author_facet Roethel, Albert
Ganzha, Maria
Wróblewska, Anna
contents A considerable number of texts encountered daily are somehow connected with each other. For example, Wikipedia articles refer to other articles via hyperlinks, scientific papers relate to others via citations or (co)authors, while tweets relate via users that follow each other or reshare content. Hence, a graph-like structure can represent existing connections and be seen as capturing the "context" of the texts. The question thus arises if extracting and integrating such context information into a language model might help facilitate a better automated understanding of the text. In this study, we experimentally demonstrate that incorporating graph-based contextualization into BERT model enhances its performance on an example of a classification task. Specifically, on Pubmed dataset, we observed a reduction in error from 8.51% to 7.96%, while increasing the number of parameters just by 1.6%. Our source code: https://github.com/tryptofanik/gc-bert
format Preprint
id arxiv_https___arxiv_org_abs_2305_11070
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Enriching language models with graph-based context information to better understand textual data
Roethel, Albert
Ganzha, Maria
Wróblewska, Anna
Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
A considerable number of texts encountered daily are somehow connected with each other. For example, Wikipedia articles refer to other articles via hyperlinks, scientific papers relate to others via citations or (co)authors, while tweets relate via users that follow each other or reshare content. Hence, a graph-like structure can represent existing connections and be seen as capturing the "context" of the texts. The question thus arises if extracting and integrating such context information into a language model might help facilitate a better automated understanding of the text. In this study, we experimentally demonstrate that incorporating graph-based contextualization into BERT model enhances its performance on an example of a classification task. Specifically, on Pubmed dataset, we observed a reduction in error from 8.51% to 7.96%, while increasing the number of parameters just by 1.6%. Our source code: https://github.com/tryptofanik/gc-bert
title Enriching language models with graph-based context information to better understand textual data
topic Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2305.11070