Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation

by   Beomsu Kim, et al.

Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due to high latency. On the other hand, retrieval models could return responses with much lower latency but show inferior performance to the large-scale generative models since the conversation quality is bounded by the pre-defined response set. To take advantage of both approaches, we propose a new training method called G2R (Generative-to-Retrieval distillation) that preserves the efficiency of a retrieval model while leveraging the conversational ability of a large-scale generative model by infusing the knowledge of the generative model into the retrieval model. G2R consists of two distinct techniques of distillation: the data-level G2R augments the dialogue dataset with additional responses generated by the large-scale generative model, and the model-level G2R transfers the response quality score assessed by the generative model to the score of the retrieval model by the knowledge distillation loss. Through extensive experiments including human evaluation, we demonstrate that our retrieval-based conversation system trained with G2R shows a substantially improved performance compared to the baseline retrieval model while showing significantly lower inference latency than the large-scale generative models.


page 1

page 2

page 3

page 4


Understanding and Improving the Exemplar-based Generation for Open-domain Conversation

Exemplar-based generative models for open-domain conversation produce re...

Building a Production Model for Retrieval-Based Chatbots

Response suggestion is an important task for building human-computer con...

Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory

For dialogue response generation, traditional generative models generate...

Production Ready Chatbots: Generate if not Retrieve

In this paper, we present a hybrid model that combines a neural conversa...

Alquist 4.0: Towards Social Intelligence Using Generative Models and Dialogue Personalization

The open domain-dialogue system Alquist has a goal to conduct a coherent...

Avoiding Echo-Responses in a Retrieval-Based Conversation System

Retrieval-based conversation systems generally tend to rank high respons...

Please sign up or login with your details

Forgot password? Click here to reset