SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling

Shahed Masoudian, Markus Frohmann, Emmanouil Karystinaios, Navid Rekabsaz, Markus Schedl
October, 2026
PDF Source Document

Abstract

SenseShift uses encoder-based mask infilling to steer the sentiment of individual sentences in longer stories and reviews.

Type
Conference paper
Publication
Findings of the Association for Computational Linguistics: EMNLP 2026
Natural Language Processing Controllable Generation
Emmanouil Karystinaios
Emmanouil Karystinaios
Senior Machine Learning Engineer and Postdoctoral Researcher

I work in music information retrieval as a Senior Machine Learning Engineer at Muse Group and a part-time Postdoctoral Researcher at Johannes Kepler University Linz.