Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10457045" target="_blank" >RIV/00216208:11320/22:10457045 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-16270-1_15" target="_blank" >https://doi.org/10.1007/978-3-031-16270-1_15</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-16270-1_15" target="_blank" >10.1007/978-3-031-16270-1_15</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising

Popis výsledku v původním jazyce

Text sentiment transfer aims to flip the sentiment polarity of a sentence (positive to negative or vice versa) while preserving its sentiment-independent content. Although current models show good results at changing the sentiment, content preservation in transferred sentences is insufficient. In this paper, we present a sentiment transfer model based on polarity-aware denoising, which accurately controls the sentiment attributes in generated text, preserving the content to a great extent and helping to balance the style-content trade-off. Our proposed model is structured around two key stages in the sentiment transfer process: better representation learning using a shared encoder and sentiment-controlled generation using separate sentiment-specific decoders. Empirical results show that our methods outperforms state-of-the-art baselines in terms of content preservation while staying competitive in terms of style transfer accuracy and fluency. Source code, data, and all other related details are availa

Název v anglickém jazyce

Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising

Popis výsledku anglicky

Text sentiment transfer aims to flip the sentiment polarity of a sentence (positive to negative or vice versa) while preserving its sentiment-independent content. Although current models show good results at changing the sentiment, content preservation in transferred sentences is insufficient. In this paper, we present a sentiment transfer model based on polarity-aware denoising, which accurately controls the sentiment attributes in generated text, preserving the content to a great extent and helping to balance the style-content trade-off. Our proposed model is structured around two key stages in the sentiment transfer process: better representation learning using a shared encoder and sentiment-controlled generation using separate sentiment-specific decoders. Empirical results show that our methods outperforms state-of-the-art baselines in terms of content preservation while staying competitive in terms of style transfer accuracy and fluency. Source code, data, and all other related details are availa

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

25th International Conference on Text, Speech and Dialogue

ISBN

978-3-031-16269-5

ISSN

—

e-ISSN

—

Počet stran výsledku

15

Strana od-do

172-186

Název nakladatele

Springer

Místo vydání

Cham, Switzerland

Místo konání akce

Brno, Czechia

Datum konání akce

6. 9. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—