Disentangled representations for manipulation of sentiment in text

Maria Larsson, Amanda Nilsson, Mikael Kågebäck, (NIPS workshop on Learning Disentangled Features: from Perception to Control)
pdf bibTex

The ability to change arbitrary aspects of a text while leaving the core message intact could have a strong impact in fields like marketing and politics by enabling e.g. automatic optimization of message impact and personalized language adapted to the receiver’s profile. In this paper we take a first step towards such a system by presenting an algorithm that can manipulate the sentiment of a text while preserving its semantics using disentangled representations. Validation is performed by examining trajectories in embedding space and analyzing transformed sentences for semantic preservation while expression of desired sentiment shift.


  title={Disentangled representations for manipulation of sentiment in text},
  author={Larsson, Maria and Nilsson, Amanda and K{\aa}geb{\"a}ck, Mikael},
  journal={arXiv preprint arXiv:1712.10066},

Leave a Reply

Your email address will not be published. Required fields are marked *