loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Mariano de Rivero ; Cristhiam Tirado and Willy Ugarte

Affiliation: Universidad Peruana de Ciencias Aplicadas (UPC), Lima, Peru

Keyword(s): Natural Language Processing, Style Transfer, GPT-2, Formalization, Meaning Preservation, Transformer.

Abstract: Style transfer is a natural language processing generation task, it consists of substituting one given writing style for another one. In this work, we seek to perform informal-to-formal style transfers in the English language. This process is shown in our web interface where the user input a informal message by text or voice. This project’s target audience are students and professionals in the need to improve the quality of their work by formalizing their texts. A style transfer is considered successful when the original semantic meaning of the message is preserved after the independent style has been replaced. This task is hindered by the scarcity of training and evaluation datasets alongside the lack of metrics. To accomplish this task we opted to utilize OpenAI’s GPT-2 Transformer-based pre-trained model. To adapt the GPT-2 to our research, we fine-tuned the model with a parallel corpus containing informal text entries paired with the equivalent formal ones. We evaluate the fine-t uned model results with two specific metrics, formality and meaning preservation. To further fine-tune the model we integrate a human-based feedback system where the user selects the best formal sentence out of the ones generated by the model. The resulting evaluations of our solution exhibit similar to improved scores in formality and meaning preservation to state-of-the-art approaches. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.217.144.32

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
de Rivero, M.; Tirado, C. and Ugarte, W. (2021). FormalStyler: GPT based Model for Formal Style Transfer based on Formality and Meaning Preservation. In Proceedings of the 13th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2021) - KDIR; ISBN 978-989-758-533-3; ISSN 2184-3228, SciTePress, pages 48-56. DOI: 10.5220/0010674300003064

@conference{kdir21,
author={Mariano {de Rivero}. and Cristhiam Tirado. and Willy Ugarte.},
title={FormalStyler: GPT based Model for Formal Style Transfer based on Formality and Meaning Preservation},
booktitle={Proceedings of the 13th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2021) - KDIR},
year={2021},
pages={48-56},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010674300003064},
isbn={978-989-758-533-3},
issn={2184-3228},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2021) - KDIR
TI - FormalStyler: GPT based Model for Formal Style Transfer based on Formality and Meaning Preservation
SN - 978-989-758-533-3
IS - 2184-3228
AU - de Rivero, M.
AU - Tirado, C.
AU - Ugarte, W.
PY - 2021
SP - 48
EP - 56
DO - 10.5220/0010674300003064
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic