Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching
This work solves a practical problem for businesses needing efficient receipt-to-POI matching in document-oriented databases, though it is incremental as it builds on existing deep retrieval techniques.
The paper tackles the problem of matching financial receipt images to corresponding places of interest in a nationwide database, addressing challenges like noisy queries and incomplete entries. The proposed deep retrieval model significantly outperforms conventional manual pattern-based methods, reducing development and maintenance costs.
Semi-structured query systems for document-oriented databases have many real applications. One particular application that we are interested in is matching each financial receipt image with its corresponding place of interest (POI, e.g., restaurant) in the nationwide database. The problem is especially challenging in the real production environment where many similar or incomplete entries exist in the database and queries are noisy (e.g., errors in optical character recognition). In this work, we aim to address practical challenges when using embedding-based retrieval for the query grounding problem in semi-structured data. Leveraging recent advancements in deep language encoding for retrieval, we conduct extensive experiments to find the most effective combination of modules for the embedding and retrieval of both query and database entries without any manually engineered component. The proposed model significantly outperforms the conventional manual pattern-based model while requiring much less development and maintenance cost. We also discuss some core observations in our experiments, which could be helpful for practitioners working on a similar problem in other domains.