Augmenting Transformers with KNN-Based Composite Memory

Angela Fan, Claire Gardent, Chloe Braud, Antoine Bordes

Keywords: knn, memory-augmented networks, language generation, dialogue

TL;DR: augment transformers with KNN-based search modules to read from multi-modal external information

Abstract: 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 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 dialogue 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 from Wikipedia, images, and human-written dialogue utterances, and show that leveraging this retrieved information improves model performance, measured by automatic and human evaluation.