论文标题
MINTL：针对任务对话系统的极简主义转移学习
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
论文作者
论文摘要
在本文中，我们提出了简约的转移学习（MINTL），以简化面向任务的对话系统的系统设计过程，并减轻对注释数据的过度依赖性。 MINTL是一个简单而有效的转移学习框架，它使我们能够插入预训练的SEQ2SEQ模型，并共同学习对话状态跟踪和对话响应的生成。与以前使用复制机制“结转”向新对话的方法不同的方法不同，我们引入了Levenshtein信念跨度（LEV），该方法允许具有最小的生成长度的有效对话状态跟踪。我们使用两个预训练的骨架：T5和Bart实例化学习框架，并在Multiwoz上对其进行评估。广泛的实验表明：1）我们的系统在端到端响应生成上建立了新的最先进的结果，2）基于MINTL的系统比低资源设置中的基线方法更强大，并且它们仅通过20 \％的培训数据获得竞争成果，而3）LEV极大地提高了推理效率。
In this paper, we propose Minimalist Transfer Learning (MinTL) to simplify the system design process of task-oriented dialogue systems and alleviate the over-dependency on annotated data. MinTL is a simple yet effective transfer learning framework, which allows us to plug-and-play pre-trained seq2seq models, and jointly learn dialogue state tracking and dialogue response generation. Unlike previous approaches, which use a copy mechanism to "carryover" the old dialogue states to the new one, we introduce Levenshtein belief spans (Lev), that allows efficient dialogue state tracking with a minimal generation length. We instantiate our learning framework with two pre-trained backbones: T5 and BART, and evaluate them on MultiWOZ. Extensive experiments demonstrate that: 1) our systems establish new state-of-the-art results on end-to-end response generation, 2) MinTL-based systems are more robust than baseline methods in the low resource setting, and they achieve competitive results with only 20\% training data, and 3) Lev greatly improves the inference efficiency.
