KG-ECO: Knowledge Graph Enhanced Entity Correction for Query Rewriting

TL;DR

KG-ECO enhances query rewriting in dialogue systems by integrating knowledge graph information for more accurate entity correction, especially in few-shot scenarios, leading to significant performance improvements.

Contribution

This work introduces a novel entity correction system that leverages knowledge graphs with graph neural networks and RoBERTa for improved query rewriting.

Findings

Performance gain over baseline methods.

Effective in few-shot learning scenarios.

Utilizes KG structural and textual information.

Abstract

Query Rewriting (QR) plays a critical role in large-scale dialogue systems for reducing frictions. When there is an entity error, it imposes extra challenges for a dialogue system to produce satisfactory responses. In this work, we propose KG-ECO: Knowledge Graph enhanced Entity COrrection for query rewriting, an entity correction system with corrupt entity span detection and entity retrieval/re-ranking functionalities. To boost the model performance, we incorporate Knowledge Graph (KG) to provide entity structural information (neighboring entities encoded by graph neural networks) and textual information (KG entity descriptions encoded by RoBERTa). Experimental results show that our approach yields a clear performance gain over two baselines: utterance level QR and entity correction without utilizing KG information. The proposed system is particularly effective for few-shot learning cases where target entities are rarely seen in training or there is a KG relation between the target entity and other contextual entities in the query.