Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

By Shereen Oraby, Lena Reed, Shubhangi Tandon, S. SharathT., Stephanie M. Lukin, Marilyn A. Walker. 2018

71 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Queens Are Powerful Too: Mitigating Gender Bias in Dialogue Generation (2019, methodology): “To create models that can generate a gender-balanced number of gendered words, we propose Conditional Training (CT) for controlling generative model output (Kikuchi et al., 2016; Fan et al., 2017; Oraby et al., 2018; See et al., 2019).”
Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring? (2018, background): “hibit less stylistic variation than their training data (Oraby et al., 2018b).”
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation (2019, methodology): “A.2 Experimental Details We adopt the 100-dimensional pretrained GloVe word embeddings (Pennington et al., 2014) as inputs of a standard machine translation sequenceto-sequence model with attention.”
Returning the N to NLP: Towards Contextually Personalized Classification Models (2020, methodology): “…et al., 2019; Wen et al., 2012; Yoon et al., 2017; McMahan et al., 2017), which are largely used e.g. in predictive writing, and in natural language generation (Oraby et al., 2018; Harrison et al., 2019), aiming e.g. at selecting and preserving a consistent personality and style within a discourse.”