Retrieval-Augmented Transformer-XL for Close-Domain Dialog Generation

Understand

Transformer-based models have demonstrated excellent capabilities of capturing patterns and structures in natural language generation and achieved state-of-the-art results in many tasks.

• In this paper we present a transformer-based model for multi-turn dialog response generation.
• Our solution is based on a hybrid approach which augments a transformer-based generative model with a novel retrieval mechanism, which leverages the memorized information in the training data via k-Nearest Neighbor search.
• Our system is evaluated on two datasets made by customer/assistant dialogs: the Taskmaster-1, released by Google and holding high quality, goal-oriented conversational data and a proprietary dataset collected from a real customer service call center.