Augmenting Transformers with KNN-Based Composite Memory for Dialogue
This addresses the challenge of maintaining topic and flow in conversations for dialogue systems, though it is incremental as it builds on existing memory-augmented architectures.
The authors tackled the problem of generative dialogue modeling by augmenting Transformers with KNN-based Information Fetching modules to access external knowledge from Wikipedia, images, and human dialogues, resulting in improved performance as measured by automatic and human evaluations.
Various machine learning tasks can benefit from access to external information of different modalities, such as text and images. Recent work has focused on learning architectures with large memories capable of storing this knowledge. We propose augmenting generative Transformer neural networks with KNN-based Information Fetching (KIF) modules. Each KIF module learns a read operation to access fixed external knowledge. We apply these modules to generative dialog modeling, a challenging task where information must be flexibly retrieved and incorporated to maintain the topic and flow of conversation. We demonstrate the effectiveness of our approach by identifying relevant knowledge required for knowledgeable but engaging dialog from Wikipedia, images, and human-written dialog utterances, and show that leveraging this retrieved information improves model performance, measured by automatic and human evaluation.