Dialog models can be greatly strengthened through grounding on various
external information, but grounded dialog corpora are usually not naturally
accessible. In this work, we focus on the few-shot learning for grounded dialog
generation (GDG). We first propose a simple prompting method for GDG tasks,
where different constructs of model input, such as the grounding source and the
conversation context, are distinguished through continuous or discrete prompts.
On three typical GDG tasks, we empirically demonstrate and analyze in-depth the
effectiveness of our method. We then conduct extensive experiments to
thoroughly investigate how our prompting method works with different
pre-trained models. We show that prompted language models perform superiorly to
conversational models, and further analyze various factors that influence the
effects of prompting. Overall, our work introduces a prompt-based perspective
to the few-shot learning for GDG tasks, and provides valuable findings and
insights for future research.

本研究提出了一种基于提示的方法，通过连续或离散提示来区分不同构建的输入，例如基础来源和会话内容，证明提示的语言模型表现优于会话模型，并进一步分析影响提示效果的各种因素，为未来研究提供了有价值的发现和见解。

探索基于提示的少样本学习用于基于对话生成的实用对话系统

Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation

We present a novel training framework for neural sequence models,
particularly for grounded dialog generation. The standard training paradigm for
these models is maximum likelihood estimation (MLE), or minimizing the
cross-entropy of the human responses. Across a variety of domains, a recurring
problem with MLE trained generative neural dialog models (G) is that they tend
to produce 'safe' and generic responses ("I don't know", "I can't tell"). In
contrast, discriminative dialog models (D) that are trained to rank a list of
candidate human responses outperform their generative counterparts; in terms of
automatic metrics, diversity, and informativeness of the responses. However, D
is not useful in practice since it cannot be deployed to have real
conversations with users.
Our work aims to achieve the best of both worlds -- the practical usefulness
of G and the strong performance of D -- via knowledge transfer from D to G. Our
primary contribution is an end-to-end trainable generative visual dialog model,
where G receives gradients from D as a perceptual (not adversarial) loss of the
sequence sampled from G. We leverage the recently proposed Gumbel-Softmax (GS)
approximation to the discrete distribution -- specifically, an RNN augmented
with a sequence of GS samplers, coupled with the straight-through gradient
estimator to enable end-to-end differentiability. We also introduce a stronger
encoder for visual dialog, and employ a self-attention mechanism for answer
encoding along with a metric learning loss to aid D in better capturing
semantic similarities in answer responses. Overall, our proposed model
outperforms state-of-the-art on the VisDial dataset by a significant margin
(2.67% on recall@10). The source code can be downloaded from
this https URL

本文提出一种新的训练神经序列模型，将判别式对话模型的知识传递到生成式对话模型中，通过 Gumbel-Softmax 逼近离散分布，建立了一个可端对端训练的生成式视觉对话模型，并在视觉对话数据集上显著优于现有模型 (10 个问题中有 2.67 个问题得分有所提高)。