Leveraging Linguistic Coordination in Reranking N-Best Candidates For End-to-End Response Selection Using BERT
Computation and Language
2021-05-31 v1
Abstract
Retrieval-based dialogue systems select the best response from many candidates. Although many state-of-the-art models have shown promising performance in dialogue response selection tasks, there is still quite a gap between R@1 and R@10 performance. To address this, we propose to leverage linguistic coordination (a phenomenon that individuals tend to develop similar linguistic behaviors in conversation) to rerank the N-best candidates produced by BERT, a state-of-the-art pre-trained language model. Our results show an improvement in R@1 compared to BERT baselines, demonstrating the utility of repairing machine-generated outputs by leveraging a linguistic theory.
Keywords
Cite
@article{arxiv.2105.13479,
title = {Leveraging Linguistic Coordination in Reranking N-Best Candidates For End-to-End Response Selection Using BERT},
author = {Mingzhi Yu and Diane Litman},
journal= {arXiv preprint arXiv:2105.13479},
year = {2021}
}
Comments
The 34th International FLAIRS Conference Proceedings, May 2021