Jilin Wang

Title: Jilin Wang - Innovator in Information Extraction

Introduction

Jilin Wang is a notable inventor based in Cambridge, MA (US). He has made significant contributions to the field of information extraction, particularly through his innovative patent that focuses on utilizing machine learning for data extraction from unstructured text documents.

Latest Patents

Jilin Wang holds a patent for a method titled "Information extraction for unstructured text documents." This invention involves training and using a machine learning model to extract data effectively. The process begins with receiving keys of interest from a user via an interface, followed by the analysis of a batch of documents containing unstructured text. The model processes the first document to extract structured text and predicts text classifications based on the user's keys of interest. The predicted classifications are then presented to the user, who can provide annotations to correct any inaccuracies. The model is subsequently retrained using these annotations, and this iterative process continues for additional documents until the model achieves a specified level of accuracy. Finally, the trained model classifies the extracted structured text in the remaining documents of the batch.

Career Highlights

Jilin Wang is currently employed at S&P Global, Inc., where he applies his expertise in machine learning and data extraction. His work has positioned him as a key player in the development of innovative solutions that enhance the processing of unstructured data.

Collaborations

Some of Jilin Wang's coworkers include Andrey Ryazanov and Baojia Tong, who contribute to the collaborative environment at S&P Global, Inc. Their combined efforts foster innovation and drive advancements in their respective fields.

Conclusion

Jilin Wang's contributions to information extraction through his patented method exemplify the intersection of technology and innovation. His work continues to influence the way unstructured data is processed and utilized in various applications.