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

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.

[1]  Zhen-Hua Ling,et al.  Enhanced LSTM for Natural Language Inference , 2016, ACL.

[2]  Anoop Cherian,et al.  The Eighth Dialog System Technology Challenge , 2019, ArXiv.

[3]  Danna Zhou,et al.  d. , 1840, Microbial pathogenesis.

[4]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[5]  Jon M. Kleinberg,et al.  Echoes of power: language effects and power differences in social interaction , 2011, WWW.

[6]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[7]  Julia Hirschberg,et al.  High Frequency Word Entrainment in Spoken Dialogue , 2008, ACL.

[8]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[9]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[10]  Yiming Yang,et al.  XLNet: Generalized Autoregressive Pretraining for Language Understanding , 2019, NeurIPS.

[11]  Jeffrey T. Hancock,et al.  Language Style Matching as a Predictor of Social Dynamics in Small Groups , 2010, Commun. Res..

[12]  Susannah B. F. Paletz,et al.  Entrainment in Multi-Party Spoken Dialogues at Multiple Linguistic Levels , 2017, INTERSPEECH.

[13]  Susan E. Brennan,et al.  LEXICAL ENTRAINMENT IN SPONTANEOUS DIALOG , 1996 .

[14]  Ying Chen,et al.  Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network , 2018, ACL.

[15]  J. Koenderink Q… , 2014, Les noms officiels des communes de Wallonie, de Bruxelles-Capitale et de la communaute germanophone.

[16]  Jatin Ganhotra,et al.  A Large-Scale Corpus for Conversation Disentanglement , 2018, ACL.

[17]  Julia Hirschberg,et al.  Measuring Acoustic-Prosodic Entrainment with Respect to Multiple Levels and Dimensions , 2011, INTERSPEECH.