面向低资源个性化对话生成的栈传播框架
A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation
- Harbin Institute of Technology（哈尔滨工业大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
针对个性化对话数据稀缺问题，本文提出堆叠一个 Transformer 编码器与两个解码器的栈传播框架，以一致性理解正则化回复生成，在低资源设置下提升回复质量与角色一致性。
中文摘要 AI 辅助
随着构建开放域对话系统的兴趣重新兴起，对话生成任务在过去几年中受到越来越多的关注。该任务通常被表述为一个条件生成问题，旨在给定对话上下文和特定约束（例如角色设定）的情况下，生成自然且有意义的回复。而保持一致的角色设定对于对话系统获得用户信任至关重要。尽管已经取得了巨大进展，但传统的基于角色设定的对话模型通常需要利用大量角色信息密集的对话样例进行训练。然而，此类角色信息密集的训练数据获取成本高昂，导致规模有限。本工作提出了一种通过将一致性理解视为回复生成正则化项，从有限训练样例中学习的新方法。为此，我们提出了一种新颖的栈传播框架，用于学习生成与理解流水线。具体而言，该框架堆叠了一个 Transformer 编码器和两个 Transformer 解码器，其中第一个解码器对回复生成进行建模，第二个解码器充当正则化器，并联合建模回复生成与一致性理解。所提框架能够受益于堆叠的编码器和解码器，从规模小得多的个性化对话数据中学习，同时保持具有竞争力的性能。在不同的低资源设置下，主观和客观评估证明，该栈传播框架在回复质量和角色一致性方面优于强基线，并在很大程度上克服了传统模型严重依赖角色信息密集对话数据的缺点。
英文摘要
With the resurgent interest in building open-domain dialogue systems, the dialogue generation task has attracted increasing attention over the past few years. This task is usually formulated as a conditional generation problem, which aims to generate a natural and meaningful response given dialogue contexts and specific constraints, such as persona. And maintaining a consistent persona is essential for the dialogue systems to gain trust from the users. Although tremendous advancements have been brought, traditional persona-based dialogue models are typically trained by leveraging a large number of persona-dense dialogue examples. Yet, such persona-dense training data are expensive to obtain, leading to a limited scale. This work presents a novel approach to learning from limited training examples by regarding consistency understanding as a regularization of response generation. To this end, we propose a novel stack-propagation framework for learning a generation and understanding pipeline.Specifically, the framework stacks a Transformer encoder and two Transformer decoders, where the first decoder models response generation and the second serves as a regularizer and jointly models response generation and consistency understanding. The proposed framework can benefit from the stacked encoder and decoders to learn from much smaller personalized dialogue data while maintaining competitive performance. Under different low-resource settings, subjective and objective evaluations prove that the stack-propagation framework outperforms strong baselines in response quality and persona consistency and largely overcomes the shortcomings of traditional models that rely heavily on the persona-dense dialogue data.
