A Persona-Based Neural Conversation Model

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 994–1003, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics A Persona-Based Neural Conversation Model Jiwei Li1* Michel Galley2 Chris Brockett2 Georgios P. Spithourakis3* Jianfeng Gao2 Bill Dolan2 1Stanford University, Dept. of Computer Science jiweil@stanford.edu 2Microsoft Research, Redmond {mgalley,chrisbkt,jfgao,billdol}@microsoft.com 3University College London, Dept. of Computer Science g.spithourakis@cs.ucl.ac.uk Abstract We present persona-based models for han- dling the issue of speaker consistency in neural response generation. A speaker model encodes personas in distributed em- beddings that capture individual charac- teristics such as background information and speaking style. A dyadic speaker- addressee model captures properties of in- teractions between two interlocutors. Our models yield qualitative performance im- provements in both perplexity and BLEU scores over baseline sequence-to-sequence models, with similar gains in speaker con- sistency as measured by human judges. 1 Introduction As conversational agents gain traction as user in- terfaces, there has been growing research inter- est in training naturalistic conversation systems from large volumes of human-to-human interac- tions (Ritter et al., 2011; Sordoni et al., 2015; Vinyals and Le, 2015; Li et al., 2016). One major is- sue for these data-driven systems is their propensity to select the response with greatest likelihood—in effect a consensus response of the humans repre- sented in the training data. Outputs are frequently vague or non-committal (Li et al., 2016), and when not, they can be wildly inconsistent, as illustrated in Table 1. In this paper, we address the challenge of consis- tency and how to endow data-driven systems with the coherent “persona” needed to model human- like behavior, whether as personal assistants, per- * The entirety of this work was conducted at Microsoft. message Where do you live now? response I live in Los Angeles. message In which city do you live now? response I live in Madrid. message In which country do you live now? response England, you? message Where were you born? response I was born in Canada. message Where are you from? response England, you? message Where did you grow up? response I grew up in Texas. message How old are you? response 16 and you? message What’s your age? response 18. message What is your major? response I’m majoring in psychology message What did you study in college? response English lit. Table 1: Inconsistent responses generated by a 4-layer SEQ2SEQ model trained on 25 million Twitter conversation snippets. sonalized avatar-like agents, or game characters.1 For present purposes, we will define PERSONA as the character that an artificial agent, as actor, plays or performs during conversational interac- tions. A persona can be viewed as a composite of elements of identity (background facts or user profile), language behavior, and interaction style. A persona is also adaptive, since an agent may need to present different facets to different human interlocutors depending on the interaction. Fortunately, neural models of conversation gen- eration (Sordoni et al., 2015; Shang et al., 2015; Vinyals and Le, 2015; Li et al., 2016) provide a straightforward …

Content truncated to 500 words