Cargando…

SentiInc: Incorporating Sentiment Information into Sentiment Transfer Without Parallel Data

Sentiment-to-sentiment transfer involves changing the sentiment of the given text while preserving the underlying information. In this work, we present a model SentiInc for sentiment-to-sentiment transfer using unpaired mono-sentiment data. Existing sentiment-to-sentiment transfer models ignore the...

Descripción completa

Detalles Bibliográficos
Autores principales: Pant, Kartikey, Verma, Yash, Mamidi, Radhika
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7148006/
http://dx.doi.org/10.1007/978-3-030-45442-5_39
Descripción
Sumario:Sentiment-to-sentiment transfer involves changing the sentiment of the given text while preserving the underlying information. In this work, we present a model SentiInc for sentiment-to-sentiment transfer using unpaired mono-sentiment data. Existing sentiment-to-sentiment transfer models ignore the valuable sentiment-specific details already present in the text. We address this issue by providing a simple framework for encoding sentiment-specific information in the target sentence while preserving the content information. This is done by incorporating sentiment based loss in the back-translation based style transfer. Extensive experiments over the Yelp dataset show that the SentiInc outperforms state-of-the-art methods by a margin of as large as [Formula: see text]11% in G-score. The results also demonstrate that our model produces sentiment-accurate and information-preserved sentences.