KG-ECO: Knowledge Graph Enhanced Entity Correction for Query Rewriting
This work addresses entity correction in query rewriting for large-scale dialogue systems, offering an incremental improvement by incorporating knowledge graph information.
The paper tackled entity errors in query rewriting for dialogue systems by proposing KG-ECO, which uses knowledge graphs to enhance entity correction, resulting in clear performance gains over baselines, particularly in few-shot learning cases.
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.