arXiv (Cornell University) · 2021 · 14 citations · 30 references
ComputingComputer ScienceComputational LinguisticsKnowledge RepresentationNatural Language ProcessingDialogue AnalysisDialogue SystemsLanguage ModelingLanguage ModelsNatural Language GenerationConversational AgentsDialog SystemsHuman-ai ConversationPersona-based DialogueUser Modeling In Dialogue
Maintaining consistent personas is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated persona-dense data are still barriers towards training robust and consistent persona-based dialogue models. In this work, we show how the challenges can be addressed by disentangling persona-based dialogue generation into two sub-tasks with a novel BERT-over-BERT (BoB) model. Specifically, the model consists of a BERT-based encoder and two BERT-based decoders, where one decoder is for response generation, and another is for consistency understanding. In particular, to learn the ability of consistency understanding from large-scale non-dialogue inference data, we train the second decoder in an unlikelihood manner. Under different limited data settings, both automatic and human evaluations demonstrate that the proposed model outperforms strong baselines in response quality and persona consistency.
30
The Measurement of Observer Agreement for Categorical Data
J. Richard Landis, Gary G. Koch · Biometrics · 1977 · 78.9K citations · Full text
A large annotated corpus for learning natural language inference
Samuel R. Bowman, Gabor Angeli, Christopher Potts et al. · 2015 · 3.5K citations · Full text
A Diversity-Promoting Objective Function for Neural Conversation Models
Jiwei Li, Michel Galley, Chris Brockett et al. · 2016 · 2K citations · Full text
Personalizing Dialogue Agents: I have a dog, do you have pets too?
Saizheng Zhang, Emily Dinan, Jack Urbanek et al. · 2018 · 1.2K citations · Full text
Computing, Computer Science, Interpersonal Communication +16