面向低资源对话状态跟踪的基于提示学习与自训练的状态值生成方法
State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Tracking
AI总结：
针对低资源对话状态跟踪中状态值获取研究不足的问题，提出基于状态值生成的SVAG框架，结合自训练和伪标签筛选估计器，在小参数量下取得了有竞争力甚至最优的性能。
摘要：
近年来，低资源对话状态跟踪（DST）受到越来越多的关注。先获取状态值再基于值生成槽位类型的思路在该任务中已取得显著进展，但状态值获取仍是一个研究不足的问题。现有基于抽取的方法无法捕捉需要理解上下文的取值，也不具备良好的泛化性。针对这些问题，我们提出一种新颖的基于状态值生成的框架SVAG，将DST分解为状态值生成和领域槽位生成两个步骤。具体而言，我们提出生成状态值的方法，并采用自训练进一步提升状态值生成效果。此外，我们设计了一个估计器，用于检测生成不完整和生成错误的情况，以在自训练过程中筛选伪标记数据。在MultiWOZ 2.1数据集上的实验结果表明，在限定模型参数量低于1000亿的设置下，我们参数量不足10亿的方法在5%、10%和25%的数据比例设置下均达到了当前最优性能。与参数量超过1000亿的模型相比，SVAG仍能取得具有竞争力的结果。
英文摘要：
Recently, low-resource dialogue state tracking (DST) has received increasing attention. First obtaining state values then based on values to generate slot types has made great progress in this task. However, obtaining state values is still an under-studied problem. Existing extraction-based approaches cannot capture values that require the understanding of context and are not generalizable either. To address these issues, we propose a novel State VAlue Generation based framework (SVAG), decomposing DST into state value generation and domain slot generation. Specifically, we propose to generate state values and use self-training to further improve state value generation. Moreover, we design an estimator aiming at detecting incomplete generation and incorrect generation for pseudo-labeled data selection during self-training. Experimental results on the MultiWOZ 2.1 dataset show that our method which has only less than 1 billion parameters achieves state-of-the-art performance under the data ratio settings of 5%, 10%, and 25% when limited to models under 100 billion parameters. Compared to models with more than 100 billion parameters, SVAG still reaches competitive results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
