Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

Shereen Oraby, Lena Reed, Shubhangi Tandon, Sharath T.S., Stephanie Lukin, Marilyn Walker

Abstract
Natural language generators for task-oriented dialogue must effectively realize system dialogue actions and their associated semantics. In many applications, it is also desirable for generators to control the style of an utterance. To date, work on task-oriented neural generation has primarily focused on semantic fidelity rather than achieving stylistic goals, while work on style has been done in contexts where it is difficult to measure content preservation. Here we present three different sequence-to-sequence models and carefully test how well they disentangle content and style. We use a statistical generator, Personage, to synthesize a new corpus of over 88,000 restaurant domain utterances whose style varies according to models of personality, giving us total control over both the semantic content and the stylistic variation in the training data. We then vary the amount of explicit stylistic supervision given to the three models. We show that our most explicit model can simultaneously achieve high fidelity to both semantic and stylistic goals: this model adds a context vector of 36 stylistic parameters as input to the hidden state of the encoder at each time step, showing the benefits of explicit stylistic supervision, even when the amount of training data is large.
Anthology ID:
W18-5019
Volume:
Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Kazunori Komatani, Diane Litman, Kai Yu, Alex Papangelis, Lawrence Cavedon, Mikio Nakano
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
180–190
Language:
URL:
https://aclanthology.org/W18-5019
DOI:
10.18653/v1/W18-5019
Bibkey:
Cite (ACL):
Shereen Oraby, Lena Reed, Shubhangi Tandon, Sharath T.S., Stephanie Lukin, and Marilyn Walker. 2018. Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pages 180–190, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators (Oraby et al., SIGDIAL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/W18-5019.pdf
PDF Search