Cargando…

Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning

Sentiment-aware intelligent systems are essential to a wide array of applications. These systems are driven by language models which broadly fall into two paradigms: Lexicon-based and contextual. Although recent contextual models are increasingly dominant, we still see demand for lexicon-based model...

Descripción completa

Detalles Bibliográficos
Autores principales: Alshaabi, Thayer, Van Oort, Colin M., Fudolig, Mikaela Irene, Arnold, Michael V., Danforth, Christopher M., Dodds, Peter Sheridan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8819185/
https://www.ncbi.nlm.nih.gov/pubmed/35141518
http://dx.doi.org/10.3389/frai.2021.783778
_version_ 1784646002332925952
author Alshaabi, Thayer
Van Oort, Colin M.
Fudolig, Mikaela Irene
Arnold, Michael V.
Danforth, Christopher M.
Dodds, Peter Sheridan
author_facet Alshaabi, Thayer
Van Oort, Colin M.
Fudolig, Mikaela Irene
Arnold, Michael V.
Danforth, Christopher M.
Dodds, Peter Sheridan
author_sort Alshaabi, Thayer
collection PubMed
description Sentiment-aware intelligent systems are essential to a wide array of applications. These systems are driven by language models which broadly fall into two paradigms: Lexicon-based and contextual. Although recent contextual models are increasingly dominant, we still see demand for lexicon-based models because of their interpretability and ease of use. For example, lexicon-based models allow researchers to readily determine which words and phrases contribute most to a change in measured sentiment. A challenge for any lexicon-based approach is that the lexicon needs to be routinely expanded with new words and expressions. Here, we propose two models for automatic lexicon expansion. Our first model establishes a baseline employing a simple and shallow neural network initialized with pre-trained word embeddings using a non-contextual approach. Our second model improves upon our baseline, featuring a deep Transformer-based network that brings to bear word definitions to estimate their lexical polarity. Our evaluation shows that both models are able to score new words with a similar accuracy to reviewers from Amazon Mechanical Turk, but at a fraction of the cost.
format Online
Article
Text
id pubmed-8819185
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-88191852022-02-08 Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning Alshaabi, Thayer Van Oort, Colin M. Fudolig, Mikaela Irene Arnold, Michael V. Danforth, Christopher M. Dodds, Peter Sheridan Front Artif Intell Artificial Intelligence Sentiment-aware intelligent systems are essential to a wide array of applications. These systems are driven by language models which broadly fall into two paradigms: Lexicon-based and contextual. Although recent contextual models are increasingly dominant, we still see demand for lexicon-based models because of their interpretability and ease of use. For example, lexicon-based models allow researchers to readily determine which words and phrases contribute most to a change in measured sentiment. A challenge for any lexicon-based approach is that the lexicon needs to be routinely expanded with new words and expressions. Here, we propose two models for automatic lexicon expansion. Our first model establishes a baseline employing a simple and shallow neural network initialized with pre-trained word embeddings using a non-contextual approach. Our second model improves upon our baseline, featuring a deep Transformer-based network that brings to bear word definitions to estimate their lexical polarity. Our evaluation shows that both models are able to score new words with a similar accuracy to reviewers from Amazon Mechanical Turk, but at a fraction of the cost. Frontiers Media S.A. 2022-01-24 /pmc/articles/PMC8819185/ /pubmed/35141518 http://dx.doi.org/10.3389/frai.2021.783778 Text en Copyright © 2022 Alshaabi, Van Oort, Fudolig, Arnold, Danforth and Dodds. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Artificial Intelligence
Alshaabi, Thayer
Van Oort, Colin M.
Fudolig, Mikaela Irene
Arnold, Michael V.
Danforth, Christopher M.
Dodds, Peter Sheridan
Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning
title Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning
title_full Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning
title_fullStr Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning
title_full_unstemmed Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning
title_short Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning
title_sort augmenting semantic lexicons using word embeddings and transfer learning
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8819185/
https://www.ncbi.nlm.nih.gov/pubmed/35141518
http://dx.doi.org/10.3389/frai.2021.783778
work_keys_str_mv AT alshaabithayer augmentingsemanticlexiconsusingwordembeddingsandtransferlearning
AT vanoortcolinm augmentingsemanticlexiconsusingwordembeddingsandtransferlearning
AT fudoligmikaelairene augmentingsemanticlexiconsusingwordembeddingsandtransferlearning
AT arnoldmichaelv augmentingsemanticlexiconsusingwordembeddingsandtransferlearning
AT danforthchristopherm augmentingsemanticlexiconsusingwordembeddingsandtransferlearning
AT doddspetersheridan augmentingsemanticlexiconsusingwordembeddingsandtransferlearning