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.
@article{arxiv.2105.09235,
title = {Retrieval-Augmented Transformer-XL for Close-Domain Dialog Generation},
author = {Giovanni Bonetta and Rossella Cancelliere and Ding Liu and Paul Vozila},
journal= {arXiv preprint arXiv:2105.09235},
year = {2021}
}
Comments
The International FLAIRS Conference Proceedings volume 34 issue 1