Augmenting Task-Oriented Dialogue Systems with Relation Extraction

TL;DR

This paper introduces the integration of relation extraction into task-oriented dialogue systems to enhance their ability to understand complex queries involving relationships between slots, simplifying annotation schemes.

Contribution

It proposes a novel method to incorporate relation extraction into dialogue pipelines, expanding their interpretative capabilities and reducing annotation complexity.

Findings

Relation extraction improves understanding of complex queries.

Simplified slot-filling schemes retain expressive power.

Enhanced dialogue system performance across domains.

Abstract

The standard task-oriented dialogue pipeline uses intent classification and slot-filling to interpret user utterances. While this approach can handle a wide range of queries, it does not extract the information needed to handle more complex queries that contain relationships between slots. We propose integration of relation extraction into this pipeline as an effective way to expand the capabilities of dialogue systems. We evaluate our approach by using an internal dataset with slot and relation annotations spanning three domains. Finally, we show how slot-filling annotation schemes can be simplified once the expressive power of relation annotations is available, reducing the number of slots while still capturing the user's intended meaning.