Elamur Research⌕
☰
home / papers / 2011 / Controlling User Perceptions of Linguistic Style: Trainable Generation of Personality Traits

Controlling User Perceptions of Linguistic Style: Trainable Generation of Personality Traits

Paper · 2011 · François Mairesse and Marilyn A. Walker

Summary

Dialogue systems gain from varying their linguistic style, but rule-based style control is hard to port and scale. Earlier statistical NLG improved fluency, yet no one had shown that its stylistic variation is perceived by listeners as intended. Mairesse and Walker present PERSONAGE, a generator with many parameters grounded in psychological research on how personality shows in language. They propose parameter estimation (PE): models trained on utterances that judges rated for personality learn to predict the generation decisions needed to express a target personality. Targets are given as continuous scores on all five Big Five traits, in any combination. This replaces discrete personality classes and avoids the costly overgenerate-and-score process. In a human evaluation, PE outputs showed recognizable stylistic differences on several traits at once and on a continuous scale. This matters because a style can be learned from rating data rather than hand-tuned, which makes it easier to move to new domains and stylistic dimensions.

Key points

  • PERSONAGE-RB, the earlier rule-based version, produced only 10 discrete personalities, one high or low extreme per trait. Its outputs were validated with the questionnaire of Gosling, Rentfrow, and Swann (2003).
  • PERSONAGE-OS ranks random paraphrases using generation-decision features, n-grams, LIWC, and the MRC psycholinguistic database. Its predictions correlated with ratings at r = .52 for agreeableness, r = .37 for extraversion, and r = .29 for emotional stability.
  • Models trained on out-of-domain data (96 personality-rated conversation extracts) performed worse than in-domain models on every trait.
  • Unlike CRAG-2, which splits blog-based personality ratings into three levels, PE models treat personality as continuous and do not need overgeneration.
  • PERSONAGE and the personality-annotated corpus are freely downloadable. The authors also offer an online demo and a tutorial on adapting the generator to new domains.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of CambridgeCambridge · United Kingdom256 works · 123,373 citations🎓University of California, Santa CruzSanta Cruz · United States38 works · 3,604 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

Cite

Cite as François Mairesse and Marilyn A. Walker. 2011. Controlling User Perceptions of Linguistic Style: Trainable Generation of Personality Traits. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00063

@article{mairesse2011controlling,
  title = {{Controlling User Perceptions of Linguistic Style: Trainable Generation of Personality Traits}},
  author = {François Mairesse and Marilyn A. Walker},
  journal = {Computational Linguistics},
  year = {2011},
  doi = {10.1162/coli\_a\_00063},
  url = {https://doi.org/10.1162/coli_a_00063}
}

References

82 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. André, Elisabeth, Thomas Rist, Susanne van Mulken, Martin Klesen, and Stephan Baldes. 2000. The automated design of believable dialogues for animated presentation teams. In J. Sullivan, S. Prevost, J. Cassell, and E. Churchill, editors, Embodied Conversational Agents. MIT Press, Cambridge, MA, page… find
  2. Bangalore, Srinivas and Owen Rambow. 2000. Exploiting a probabilistic hierarchical model for generation. In Proceedings of the 18th International Conference on Computational Linguistics (COLING), pages 42–48, Saarbrücken.
  3. Barzilay, Regina and Lillian Lee. 2002. Bootstrapping lexical choice via multiple-sequence alignment. In Proceedings of EMNLP, pages 164–171, Philadelphia, PA. find
  4. Belz, Anja. 2005. Corpus-driven generation of weather forecasts. In Proceedings of the Third Corpus Linguistics Conference, Birmingham. http://www.icwsm.org/papers/paper30.html. ↗
  5. Belz, Anja. 2008. Automatic generation of weather forecast texts using comprehensive probabilistic generation-space models. Natural Language Engineering, 14(4):431–455. find
  6. Biber, Douglas. 1988. Variation Across Speech and Writing. Cambridge University Press. find
  7. Bouayad-Agha, Nadjet, Donia R. Scott, and Richard Power. 2000. Integrating content and style in documents: A case study of patient information leaflets. Information Design Journal, 9(2-3):161–176. find
  8. Brennan, Susan E. and Herbert H. Clark. 1996. Conceptual pacts and lexical choice in conversation. Journal of Experimental Psychology: Learning, Memory And Cognition, 22:1482–1493. find
  9. Cassell, Justine and Timothy Bickmore. 2003. Negotiated collusion: Modeling social language and its relationship effects in intelligent agents. User Modeling and User-Adapted Interaction, 13:89–132. find
  10. Chambers, Nathanael and James Allen. 2004. Stochastic language generation in a dialogue system: Toward a domain independent generator. In Proceedings of the 5th SIGdial Workshop on Discourse and Dialogue, pages 9–18, Cambridge, MA. find
  11. Chklovski, Timothy and Patrick Pantel. 2004. V ERB O CEAN : Mining the Web for fine-grained semantic verb relations. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 33–40, Barcelona. find
  12. Clark, Herbert H. and Susan E. Brennan. 1991. Perspectives on socially shared cognition. In L. B. Resnick, J. Levine, and S. D. Bahrend, editors, Grounding in Communication, pages 127–149, American Psychological Association, Washington, DC. find
  13. Coltheart, Max. 1981. The MRC psycholinguistic database. Quarterly Journal of Experimental Psychology, 33A:497–505. find
  14. Costa, Paul T. and Robert R. McCrae, 1992. NEO PI-R Professional Manual. Psychological Assessment Resources, Odessa, FL. find
  15. Daumé III, Hal. 2007. Frustratingly easy domain adaptation. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL), pages 256–263, Prague.
  16. Dunbar, Robin. 1996. Grooming, Gossip, and the Evolution of Language. Harvard University Press, Cambridge, MA. find
  17. Fellbaum, Christiane. 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, MA. find
  18. Funder, David C. 1997. The Personality Puzzle. W. W. Norton & Company, New York, 2nd edition. find
  19. Furnham, Adrian. 1990. Language and personality. In H. Giles and W. Robinson, editors, Handbook of Language and Social Psychology. Wiley, Chichester, pages 73–95. find
  20. Goffman, Erving. 1970. Strategic Interaction. Blackwell, Oxford. find
  21. Goldberg, Lewis R. 1990. An alternative “description of personality”: The Big-Five factor structure. Journal of Personality and Social Psychology, 59:1216–1229. find
  22. Gosling, Samuel D., Sam Gaddis, and Simine Vazire. 2007. Personality impressions based on facebook profiles. In Proceedings of the International Conference on Weblogs and Social Media, Boulder, CO. http://www.icwsm.org/papers/paper30.html. ↗
  23. Gosling, Samuel D., Peter J. Rentfrow, and William B. Swann. 2003. A very brief measure of the big five personality domains. Journal of Research in Personality, 37:504–528. find
  24. Green, Stephen J. and Chrysanne DiMarco. 1996. Stylistic decision-making in natural language generation. Lecture Notes in Computer Science, Trends in Natural Language Generation: An Artificial Intelligence Perspective, 1036:125–143. find
  25. Higashinaka, Ryuichiro, Marilyn A. Walker, and Rashmi Prasad. 2007. An unsupervised method for learning generation lexicons for spoken dialogue systems by mining user reviews. ACM Transactions on Speech and Language Processing, 4(4):Article 8. find
  26. Hovy, Eduard. 1988. Generating Natural Language Under Pragmatic Constraints. Lawrence Erlbaum Associates, Mahwah, NJ. find
  27. Inkpen, Diana Zaiu and Graeme Hirst. 2004. Near-synonym choice in natural language generation. In Nicolas Nicolov, Kalina Bontcheva, Galia Angelova, and Ruslan Mitkov, editors, Recent Advances in Natural Language Processing III, pages 141–152, John Benjamins Publishing Company, Amsterdam. find
  28. Isard, Amy, Carsten Brockmann, and Jon Oberlander. 2006. Individuality and alignment in generated dialogues. In Proceedings of the 4th International Natural Language Generation Conference (INLG), pages 22–29, Sydney. find
  29. John, Oliver P., Eileen M. Donahue, and Robert L. Kentle. 1991. The “Big Five” Inventory: Versions 4a and 5b. University of California, Berkeley, Institute of Personality and Social Research. find
  30. Jordan, Pamela W. 2000. Intentional Influences on Object Redescriptions in Dialogue: Evidence from an Empirical Study. Ph.D. thesis, Intelligent Systems Program, University of Pittsburgh. find
  31. Kittredge, Richard, Tanya Korelsky, and Owen Rambow. 1991. On the need for domain communication knowledge. Computational Intelligence, 7(4):305–314. find
  32. Labov, William. 2006. The Social Stratification of English in New York City. Cambridge University Press. find
  33. Langkilde, Irene and Kevin Knight. 1998. Generation that exploits corpus-based statistical knowledge. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics (ACL), pages 704–710, Montreal.
  34. Langkilde-Geary, Irene. 2002. An empirical verification of coverage and correctness for a general-purpose sentence generator. In Proceedings of the International Conference on Natural Language Generation, pages 17–24, Harriman, NY.
  35. Lavoie, Benoit and Owen Rambow. 1997. A fast and portable realizer for text generation systems. In Proceedings of the 3rd Conference on Applied Natural Language Processing, pages 265–268, Washington, D.C.
  36. Lester, James C., Brian Stone, and Gary Stelling. 1999. Lifelike pedagogical agents for mixed-initiative problem solving in constructivist learning environments. User Modeling and User-Adapted Interaction, 9(1-2):1–44. find
  37. Lester, James C., Stuart G. Towns, and Patrick J. Fitzgerald. 1999. Achieving affective impact: Visual emotive communication in lifelike pedagogical agents. The International Journal of Artificial Intelligence in Education, 10(3-4):278–291. find
  38. Levelt, Willem J. and Stephanie Kelter. 1982. Surface form and memory in question answering. Cognitive Psychology, 14(1):78–106. find
  39. Litman, Diane J. and Kate Forbes-Riley. 2004. Predicting student emotions in computer–human tutoring dialogues. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL), pages 352–359, Barcelona. find
  40. Litman, Diane J. and Kate Forbes-Riley. 2006. Recognizing student emotions and attitudes on the basis of utterances in spoken tutoring dialogues with both human and computer tutors. Speech Communication, 48(5):559–590. find
  41. Mairesse, François. 2008. Learning to Adapt in Dialogue Systems: Data-driven Models for Personality Recognition and Generation. Ph.D. thesis, Department of Computer Science, University of Sheffield. find
  42. Mairesse, François, Milica Gašić, Filip Jurčı́ček, Simon Keizer, Blaise Thomson, Kai Yu, and Steve Young. 2010. Phrase-based statistical language generation using graphical models and active learning. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (AC… find
  43. Mairesse, François and Marilyn A. Walker. 2007. PERSONAGE: Personality generation for dialogue. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL), pages 496–503, Prague. find
  44. Mairesse, François and Marilyn A. Walker. 2010. Towards personality-based user adaptation: Psychologically-informed stylistic language generation. User Modeling and User-Adapted Interaction, 20(3):227–278. find
  45. Mairesse, François, Marilyn A. Walker, Matthias R. Mehl, and Roger K. Moore. 2007. Using linguistic cues for the automatic recognition of personality in conversation and text. Journal of Artificial Intelligence Research (JAIR), 30:457–500.
  46. Marcus, David K., Scott O. Lilienfeld, John F. Edens, and Norman G. Poythress. 2006. Is antisocial personality disorder continuous or categorical? A taxometric analysis. Psychological Medicine, 36(11):1571–1582. find
  47. McQuiggan, Scott W., Bradford W. Mott, and James C. Lester. 2008. Modeling self-efficacy in intelligent tutoring systems: An inductive approach. User Modeling and User-Adapted Interaction, 18(1):81–123. find
  48. Mehl, Matthias R., Samuel D. Gosling, and James W. Pennebaker. 2006. Personality in its natural habitat: Manifestations and implicit folk theories of personality in daily life. Journal of Personality and Social Psychology, 90:862–877. find
  49. Nakatsu, Crystal and Michael White. 2006. Learning to say it well: Reranking realizations by predicted synthesis quality. In Proceedings of the 44th Annual Meeting of the Association for Computational Linguistics (ACL), pages 1113–1120. find
  50. Norman, Warren T. 1963. Toward an adequate taxonomy of personality attributes: Replicated factor structure in peer nomination personality rating. Journal of Abnormal and Social Psychology, 66:574–583. find
  51. Paiva, Daniel S. and Roger Evans. 2004. A framework for stylistically controlled generation. In Proceedings of the International Conference on Natural Language Generation, pages 120–129, Sydney. find
  52. Paiva, Daniel S. and Roger Evans. 2005. Empirically-based control of natural language generation. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL), pages 58–65, Ann Arbor, MI. find
  53. Paris, Cécile and Donia R. Scott. 1994. Stylistic variation in multilingual instructions. In Proceedings of the 7th International Workshop on Natural Language Generation, pages 45–52, Kennebunkport, ME. find
  54. Pennebaker, James W., Martha E. Francis, and Roger J. Booth. 2001. find
  55. Inquiry and Word Count: LIWC 2001. Lawrence Erlbaum Associates, Mahwah, NJ. find
  56. Pennebaker, James W. and Laura A. King. 1999. Linguistic styles: Language use as an individual difference. Journal of Personality and Social Psychology, 77:1296–1312. find
  57. Pickering, Martin J. and Simon Garrod. 2004. Towards a mechanistic theory of dialogue. Behavioral and Brain Sciences, 27:169–225. find
  58. Piwek, Paul. 2003. A flexible pragmatics-driven language generator for animated agents. In Proceedings of the Annual Meeting of the European Chapter of the Association for Computational Linguistics (EACL), pages 151–154, Budapest. find
  59. Pollack, Martha E. 1991. Overloading intentions for efficient practical reasoning. Noûs, 25:513–536. find
  60. Porayska-Pomsta, Kaska and Chris Mellish. 2004. Modelling politeness in natural language generation. In Proceedings of the International Conference on Natural Language Generation, pages 141–150, Sydney. find
  61. Power, Richard, Donia R. Scott, and Nadjet Bouayad-Agha. 2003. Generating texts with style. In Proceedings of the 4th International Conference on Intelligent Text Processing and Computational Linguistics, pages 444–452, Mexico City. find
  62. Rambow, Owen, Monica Rogati, and Marilyn A. Walker. 2001. Evaluating a trainable sentence planner for a spoken dialogue travel system. In Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL), pages 434–441, Toulouse. find
  63. Reiter, Ehud and Robert Dale. 2000. Building Natural Language Generation Systems. Cambridge University Press. find
  64. Scherer, Klaus R. 1979. Personality markers in speech. In K. R. Scherer and H. Giles, editors, Social Markers in Speech. Cambridge University Press, pages 147–209. find
  65. Scott, Donia R. and Clarisse Sieckenius de Souza. 1990. Getting the message across in RST-based text generation. In R. Dale, C. Mellish, and M. Zock, editors, Current Research in Natural Language Generation. Academic Press, London, pages 47–73.
  66. Singh, Satinder, Diane J. Litman, Michael Kearns, and Marilyn A. Walker. 2002. Optimizing dialogue management with reinforcement learning: Experiments with the NJFun system. Journal of Artificial Intelligence Research, 16:105–133. find
  67. Snyder, Benjamin and Regina Barzilay. 2007. Database-text alignment via structured multilabel classification. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 1713–1718. find
  68. Srivastava, Sanjay, Steve Guglielmo, and Jennifer S. Beer. 2010. Perceiving others’ personalities: Examining the dimensionality, assumed similarity to the self, and stability of perceiver effects. Journal of Personality and Social Psychology, 98(3):520–534. find
  69. Stent, Amanda and Hui Guo. 2005. A new data-driven approach for multimedia presentation generation. In Proceedings of EuroIMSA, Grindelwald. http://www.actapress.com/Content of Proceeding. aspx?ProceedingID=293. ↗
  70. Stent, Amanda, Rashimi Prasad, and Marilyn A. Walker. 2004. Trainable sentence planning for complex information presentations in spoken dialog systems. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL), pages 79–86, Barcelona. find
  71. Stone, Matthew and Bonnie Webber. 1998. Textual economy through close coupling of syntax and semantics. In Proceedings of the 1998 International Workshop on Natural Language Generation, pages 178–187, Niagara-on-the-Lake. find
  72. Tapus, Adriana and Maja Mataric. 2008. Socially assistive robots: The link between personality, empathy, physiological signals, and task performance. In Proceedings of the AAAI Spring Symposium on Emotion, Personality and Social Behavior, pages 133–140, Palo Alto, CA. find
  73. Vogel, Klaus and Sigrid Vogel. 1986. L’interlangue et la personalité de l’apprenant. International Journal of Applied Linguistics, 24(1):48–68. find
  74. Walker, Marilyn A. 1993. Informational Redundancy and Resource Bounds in Dialogue. Ph.D. thesis, University of Pennsylvania. find
  75. Walker, Marilyn A., Janet E. Cahn, and Stephen J. Whittaker. 1997. Improvising linguistic style: Social and affective bases for agent personality. In Proceedings of the 1st Conference on Autonomous Agents, pages 96–105, Marina Del Rey, CA. find
  76. Walker, Marilyn A., Jeanne C. Fromer, and Shrikanth Narayanan. 1998. Learning optimal dialogue strategies: A case study of a spoken dialogue agent for email. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics, COLING/ACL 98, pages 1345–1352, Montreal. find
  77. Walker, Marilyn A. and Owen Rambow. 2002. Spoken language generation. Computer Speech and Language, Special Issue on Spoken Language Generation, 16(3-4):273–281. find
  78. Walker, Marilyn A., Owen Rambow, and Monica Rogati. 2002. Training a sentence planner for spoken dialogue using boosting. Computer Speech and Language, 16(3-4):409–433. find
  79. Walker, Marilyn A., Amanda Stent, François Mairesse, and Rashmi Prasad. 2007. Individual and domain adaptation in sentence planning for dialogue. Journal of Artificial Intelligence Research (JAIR), 30:413–456. find
  80. Wang, Ning, W. Lewis Johnson, Richard E. Mayer, Paola Rizzo, Erin Shaw, and Heather Collins. 2005. The politeness effect: Pedagogical agents and learning gains. Frontiers in Artificial Intelligence and Applications, 125:686–693. find
  81. White, Michael, Rajakrishnan Rajkumar, and Scott Martin. 2007. Towards broad coverage surface realization with CCG. In Proceedings of the Workshop on Using Corpora for NLG: Language Generation and Machine Translation, pages 22–30, Copenhagen.
  82. Witten, Ian H. and Eibe Frank. 2005. Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, San Francisco, CA. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/mairesse-2011-controlling-user-perceptions-linguistic-style/