Unsupervised Slot Schema Induction for Task-oriented Dialog

TL;DR

This paper introduces an unsupervised method for inducing slot schemas from unlabeled dialog data, reducing the need for manual schema design in task-oriented dialog systems.

Contribution

It presents a novel data-driven approach leveraging language models and clustering to automatically induce slot schemas without supervision.

Findings

Significant improvement over supervised baselines in schema induction accuracy.

Effective schemas enhance dialog state tracking and response generation.

Method applicable to multiple dialog datasets like MultiWoz and SGD.

Abstract

Carefully-designed schemas describing how to collect and annotate dialog corpora are a prerequisite towards building task-oriented dialog systems. In practical applications, manually designing schemas can be error-prone, laborious, iterative, and slow, especially when the schema is complicated. To alleviate this expensive and time consuming process, we propose an unsupervised approach for slot schema induction from unlabeled dialog corpora. Leveraging in-domain language models and unsupervised parsing structures, our data-driven approach extracts candidate slots without constraints, followed by coarse-to-fine clustering to induce slot types. We compare our method against several strong supervised baselines, and show significant performance improvement in slot schema induction on MultiWoz and SGD datasets. We also demonstrate the effectiveness of induced schemas on downstream applications including dialog state tracking and response generation.