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

2021/05/27 by Yu, Mingzhi, Litman, Diane
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2105.13479

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.

Related

• Do Response Selection Models Really Know What's Next? Utterance\n Manipulation Strategies for Multi-turn Response Selection
• Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
• TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue
• RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection
• A Systematic Evaluation of Response Selection for Open Domain Dialogue