Xiaoyu Sun

Title: Innovations by Xiaoyu Sun in Document Entity Extraction

Introduction

Xiaoyu Sun is an innovative inventor based in Sunnyvale, CA (US). She has made significant contributions to the field of document entity extraction through her research and patent applications. Although she currently holds no granted patents, her work demonstrates a commitment to advancing technology in this area.

Latest Patent Applications

Xiaoyu Sun's notable patent application is titled "Document Entity Extraction Using Machine-Learned Models." This application describes systems and methods for performing document entity extraction. The method includes receiving an inference document and a target schema. It also involves generating one or more document inputs from the inference document and one or more schema inputs from the target schema. For each combination of the document input and schema input, the method obtains one or more extraction inputs by generating a respective extraction input based on the combination. The respective extraction input is then provided to the machine-learned model, which produces an output based on the extraction. Additionally, the method validates the extracted entity data based on reference spatial locations and inference spatial locations, ultimately outputting the validated extracted entity data.

Conclusion

Xiaoyu Sun's work in document entity extraction showcases her innovative spirit and dedication to leveraging machine learning for practical applications. Her contributions are poised to influence the future of this technology.