Leveraging Linguistic Coordination in Reranking N-Best Candidates For End-to-End Response Selection Using BERT

Authors

  • Mingzhi Yu University of Pittsburgh
  • Diane Litman

DOI:

https://doi.org/10.32473/flairs.v34i1.128491

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.

Downloads

Published

2021-04-18

How to Cite

Yu, M., & Litman, D. (2021). Leveraging Linguistic Coordination in Reranking N-Best Candidates For End-to-End Response Selection Using BERT. The International FLAIRS Conference Proceedings, 34. https://doi.org/10.32473/flairs.v34i1.128491

Issue

Section

Special Track: Applied Natural Language Processing