Unsupervised Neural Stylistic Text Generation using Transfer learning and Adapters
This addresses the need for consistent persona in conversational agents without expensive data annotation, though it is incremental as it builds on existing transfer learning methods.
The paper tackles the problem of generating stylistic text for conversational systems by proposing a transfer learning framework that updates only 0.3% of model parameters, improving style generation by 200% over baselines while maintaining content relevance.
Research has shown that personality is a key driver to improve engagement and user experience in conversational systems. Conversational agents should also maintain a consistent persona to have an engaging conversation with a user. However, text generation datasets are often crowd sourced and thereby have an averaging effect where the style of the generation model is an average style of all the crowd workers that have contributed to the dataset. While one can collect persona-specific datasets for each task, it would be an expensive and time consuming annotation effort. In this work, we propose a novel transfer learning framework which updates only $0.3\%$ of model parameters to learn style specific attributes for response generation. For the purpose of this study, we tackle the problem of stylistic story ending generation using the ROC stories Corpus. We learn style specific attributes from the PERSONALITY-CAPTIONS dataset. Through extensive experiments and evaluation metrics we show that our novel training procedure can improve the style generation by 200 over Encoder-Decoder baselines while maintaining on-par content relevance metrics with