Controlling User Perceptions of Linguistic Style: Trainable Generation of Personality Traits
By François Mairesse, Marilyn A. Walker. 2011
159 citations recorded by the source corpus.
Recent work in natural language generation has begun to take linguistic variation into account, developing algorithms that are capable of modifying the system's linguistic style based either on the user's linguistic style or other factors, such as personality or politeness. While stylistic control has traditionally relied on handcrafted rules, statistical methods are likely to be needed for generation systems to scale to the production of the large range of variation observed in human dialogues. Previous work on statistical natural language generation (SNLG) has shown that the grammaticality and naturalness of generated utterances can be optimized from data; however these data-driven methods have not been shown to produce stylistic variation that is perceived by humans in the way that the system intended. This paper describes Personage, a highly parameterizable language generator whose parameters are based on psychological findings about the linguistic reflexes of personality. We present a novel SNLG method which uses parameter estimation models trained on personality-annotated data to predict the generation decisions required to convey any combination of scalar values along the five main dimensions of personality. A human evaluation shows that parameter estimation models produce recognizable stylistic variation along multiple dimensions, on a continuous scale, and without the computational cost incurred by overgeneration techniques.
Subfields: Artificial Intelligence, Natural Language Generation
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
- Jianfeng Gao
- Ondrej Dusek
- Richard Socher
- Percy Liang
- Verena Rieser
- Mohit Bansal
- Minlie Huang
- Caiming Xiong
In Natural Language Generation
- Lena Reed
- Shereen Oraby
- Emiel Krahmer
- Marilyn A. Walker
- Michael Auli
- David Grangier
- Rémi Lebret
- Albert Gatt
Citations in the corpus
- Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems (2015, background): “These systems include specific trainable modules within the generation framework to allow the model to adapt to different domains (Walker et al., 2007), or reproduce certain style (Mairesse and Walker, 2011).”
- Neural Text Generation from Structured Data with Application to the Biography Domain (2016, methodology): “At the intersection of rule-based and statistical methods, hybrid systems aim at leveraging human contributed rules and corpus statistics (Langk-ilde and Knight, 1998; Soricut and Marcu, 2006; Mairesse and Walker, 2011).”
- Controlling Linguistic Style Aspects in Neural Language Generation (2017, background): “Some works tackling stylistic control of text produced in a rule-based generation system include the works of Power et al. (2003); Reiter and Williams (2010); Hovy (1987); Bateman and Paris (1989) (see (Mairesse and Walker, 2011) for a comprehensive review).”
- Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “An interesting outcome of the evaluation with human subjects reported by Mairesse and Walker (2011) is that readers vary significantly in their judgements of what personality is actually reflected by a given text.”
- On learning and representing social meaning in NLP: a sociolinguistic perspective (2021, background): “There is a large body of work on generating text in specific styles (e.g., Edmonds and Hirst (2002); Ficler and Goldberg (2017); Mairesse and Walker (2011)).”
- Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems (2018, background): “Corpus-based approaches (Oh and Rudnicky, 2000; Mairesse and Walker, 2011) learn to generate natural language directly from data without pre-defined rules.”
- A Context-aware Natural Language Generation Dataset for Dialogue Systems (2016, unknown): “Their scalability is also limited (Mairesse and Walker, 2011).”
- Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems (2018, background): “, 2007), and controlling user perceptions of linguistic style (Mairesse and Walker, 2011).”
- PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits (2023, background): “…footprints (Farnadi et al., 2013; Oberlander and Nowson, 2006; Skowron et al., 2016; Tadesse et al., 2018), and personalized dialogue generation (Mairesse and Walker, 2007, 2011; Zhang et al., 2018; Qian et al., 2018) including stylistic transfer of personality traits such as formality and…”
- A survey on empathetic dialogue systems (2020, background): “On the other hand, personality affects the way of communication in various manners including both linguistic style [99] and acoustic traits [100].”
- Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring? (2018, methodology): “We populate PERSONAGE with the syntax/meaning mappings that it needs to produce output for the E2E meaning representations, and then automatically produce a very large (204,955 utterance/MR pairs) systematically varied sentence planning corpus.”
- Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators (2018, methodology): “To use PERSONAGE to create training data mapping the same MR to multiple personality-based variants, we set values for all of the parameters in Table 3 using the stylistic models defined by Mairesse and Walker (2010) for the following”