Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System
read the original abstract
Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set. In the practical application, a reliable dialogue system should know what it does not know. In this paper, we introduce a new task, Novel Slot Detection (NSD), in the task-oriented dialogue system. NSD aims to discover unknown or out-of-domain slot types to strengthen the capability of a dialogue system based on in-domain training data. Besides, we construct two public NSD datasets, propose several strong NSD baselines, and establish a benchmark for future work. Finally, we conduct exhaustive experiments and qualitative analysis to comprehend key challenges and provide new guidance for future directions.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports
Key coverage of a canonical inventory is the dominant factor for accurate field extraction from OCR clinical reports using a small BERT model.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.