Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain
This addresses the challenge of creating persona-grounded dialogue agents in diverse settings without costly new data annotation, though it is incremental as it builds on existing persona extraction and NLI techniques.
The paper tackled the problem of automatically extracting persona information from dialogue in new domains like fantasy, where existing models trained on real-world data perform poorly, by introducing a natural language inference method for post-hoc adaptation, which resulted in higher-quality persona extraction with less human annotation.
While valuable datasets such as PersonaChat provide a foundation for training persona-grounded dialogue agents, they lack diversity in conversational and narrative settings, primarily existing in the "real" world. To develop dialogue agents with unique personas, models are trained to converse given a specific persona, but hand-crafting these persona can be time-consuming, thus methods exist to automatically extract persona information from existing character-specific dialogue. However, these persona-extraction models are also trained on datasets derived from PersonaChat and struggle to provide high-quality persona information from conversational settings that do not take place in the real world, such as the fantasy-focused dataset, LIGHT. Creating new data to train models on a specific setting is human-intensive, thus prohibitively expensive. To address both these issues, we introduce a natural language inference method for post-hoc adapting a trained persona extraction model to a new setting. We draw inspiration from the literature of dialog natural language inference (NLI), and devise NLI-reranking methods to extract structured persona information from dialogue. Compared to existing persona extraction models, our method returns higher-quality extracted persona and requires less human annotation.