Dialogue state tracking (DST) is a core sub-module of a dialogue system, which aims to extract the appropriate belief state (domain-slot-value) from a system and user utterances. Most previous studies have attempted to improve performance by increasing the size of the pre-trained model or using additional features such as graph relations. In this study, we propose dialogue state tracking with entity adaptive pre-training (DSTEA), a system in which key entities in a sentence are more intensively trained by the encoder of the DST model. DSTEA extracts important entities from input dialogues in four ways, and then applies selective knowledge masking to train the model effectively. Although DSTEA conducts only pre-training without directly infusing additional knowledge to the DST model, it achieved better performance than the best-known benchmark models on MultiWOZ 2.0, 2.1, and 2.2. The effectiveness of DSTEA was verified through various comparative experiments with regard to the entity type and different adaptive settings.
翻译:对话状态跟踪(DST)是一个对话系统的核心子模块,目的是从一个系统和用户的语句中提取适当的信仰状态(域数值),目的是从一个系统和用户的语句中提取适当的知识状态(域数值),以往的多数研究都试图通过增加培训前模式的规模或利用图示关系等额外特征来改进绩效。在本研究中,我们提议与实体适应性培训前跟踪(DSTA)对话状态,该系统中的关键实体得到DSTA模式的编码器的更密集培训。 DSTEA以四种方式从输入对话中提取重要实体,然后将选择性的知识掩码用于有效培训模型。虽然DSTEA只进行预培训,而没有直接将更多知识注入DST模式,但比MultiWOZ 2.0、2.1和2.2.最著名的基准模型取得更好的绩效。 DSTEA的有效性通过对实体类型和不同适应环境的各种比较试验得到验证。