利用生成式对话状态推理变革槽位模式归纳
Transforming Slot Schema Induction with Generative Dialogue State Inference
AI总结:
本文提出 GenDSI 生成式对话状态推理方法,在无任务先验知识下生成槽位名称与值并聚类形成槽位模式,在 MultiWOZ 和 SGD 上超越 SSI 既有最优方法。
摘要:
定义槽位模式以表示任务导向对话系统状态的挑战由槽位模式归纳(Slot Schema Induction,SSI)解决,其目标是从无标注对话数据中自动归纳槽位。以往方法通过对直接从对话文本中抽取的值片段进行聚类来归纳槽位,而本文展示了使用生成式方法发现槽位的能力。通过训练一个模型,在没有任何先验任务知识的情况下生成可概括关键对话信息的槽位名称和值,本文的 SSI 方法发现了用于表示对话状态的高质量候选信息。这些发现的槽位—值候选可以轻松聚类为统一的槽位模式,并且与人工编写的模式高度一致。在 MultiWOZ 和 SGD 数据集上的实验比较表明,生成式对话状态推理(Generative Dialogue State Inference,GenDSI)在 SSI 任务的多个方面优于此前的最先进方法。
英文摘要:
The challenge of defining a slot schema to represent the state of a task-oriented dialogue system is addressed by Slot Schema Induction (SSI), which aims to automatically induce slots from unlabeled dialogue data. Whereas previous approaches induce slots by clustering value spans extracted directly from the dialogue text, we demonstrate the power of discovering slots using a generative approach. By training a model to generate slot names and values that summarize key dialogue information with no prior task knowledge, our SSI method discovers high-quality candidate information for representing dialogue state. These discovered slot-value candidates can be easily clustered into unified slot schemas that align well with human-authored schemas. Experimental comparisons on the MultiWOZ and SGD datasets demonstrate that Generative Dialogue State Inference (GenDSI) outperforms the previous state-of-the-art on multiple aspects of the SSI task.
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。