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.
翻译:尽管在开放式对话中大规模基因变异模型的显著表现,但众所周知,由于高悬浮度,在建立实时对话系统方面,这些模型对于建立实时对话系统的实用性不那么明显。另一方面,检索模型可以以低得多的延迟度返回反应,但与大规模基因变异模型相比,其性能却不如大规模基因变异模型,因为对话质量受预先界定的整套反应组合的约束。为了利用这两种方法,我们提议一种新的培训方法,即G2R(从恢复到检索蒸馏法),以保持检索模型的效率,同时利用大规模基因变异模型的谈话能力,将基因变异模型的知识引入检索模型。G2R由两种不同的蒸馏技术组成:数据级G2R(G2R)将对话数据集与由大规模基因变异模型产生的额外反应加强,而模型G2R(G2R)则将由基因变异模型评估的响应质量评分转到知识蒸馏模型的恢复模型的得分。通过广泛的实验,包括人类评价,我们证明我们的恢复-基于基因变异模型,同时与G2R(G2R)模型相比,在大幅度改进了大规模的基因变真化模型。