@article{Bonetta_Cancelliere_Liu_Vozila_2021, title={Retrieval-Augmented Transformer-XL for Close-Domain Dialog Generation}, volume={34}, url={https://journals.flvc.org/FLAIRS/article/view/128369}, DOI={10.32473/flairs.v34i1.128369}, abstractNote={<div class="page" title="Page 1"> <div class="layoutArea"> <div class="column"> <p>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. Both achieve better BLEU scores over strong baselines.</p> </div> </div> </div>}, journal={The International FLAIRS Conference Proceedings}, author={Bonetta, Giovanni and Cancelliere, Rossella and Liu, Ding and Vozila, Paul}, year={2021}, month={Apr.} }