论文标题
一个简单的面向任务对话的语言模型
A Simple Language Model for Task-Oriented Dialogue
论文作者
论文摘要
面向任务的对话通常分解为三个任务：了解用户输入，确定操作和生成响应。尽管这样的分解可能建议为每个子任务提供一个专用模型，但我们发现一种简单的统一方法会导致多WOB数据集中的最新性能。 SimpleTOD是一种以任务为导向对话的简单方法，它使用单个因果语言模型，该模型在所有子任务上训练有素作为单个序列预测问题。这使SimpleTod能够完全利用预先训练的开放式域，因果语言模型（例如GPT-2）的转移学习。 SimpleTod在对话状态跟踪的联合目标准确性方面改进了先前的最新目标，我们的分析揭示了在这种情况下对嘈杂注释的鲁棒性。 SimpleTOD还将用于评估行动决策和响应生成的主要指标在端到端设置中：将率提高8.1点，成功率提高9.7分，并将得分合并为7.2分。
Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified approach leads to state-of-the-art performance on the MultiWOZ dataset. SimpleTOD is a simple approach to task-oriented dialogue that uses a single, causal language model trained on all sub-tasks recast as a single sequence prediction problem. This allows SimpleTOD to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2. SimpleTOD improves over the prior state-of-the-art in joint goal accuracy for dialogue state tracking, and our analysis reveals robustness to noisy annotations in this setting. SimpleTOD also improves the main metrics used to evaluate action decisions and response generation in an end-to-end setting: inform rate by 8.1 points, success rate by 9.7 points, and combined score by 7.2 points.
