Ruiyi Zhang

Title: Innovations of Ruiyi Zhang in Natural Language Processing

Introduction

Ruiyi Zhang is a prominent inventor based in Santa Clara, CA, known for his contributions to the field of natural language processing (NLP). With a total of four patents to his name, Zhang has made significant strides in improving machine learning models, particularly in named entity recognition and continual learning.

Latest Patents

One of Zhang's latest patents is titled "Generating an improved named entity recognition model using noisy data with a self-cleaning discriminator model." This innovation describes systems and methods that train a named entity recognition (NER) model using noisy training data through a self-cleaning discriminator model. The disclosed systems utilize a self-cleaning guided denoising framework to enhance NER learning on noisy data. An auxiliary discriminator model is employed to correct noise in the training data while the NER model is being trained. This approach allows for the detection and reweighting of noisy NER labels, improving the overall accuracy of the model.

Another notable patent is "Teaching a machine classifier to recognize a new class." This technology describes a machine classifier that can continually learn new classes through a continual few-shot learning approach. Initially, the classifier is trained to identify multiple classes through conventional methods. To learn a new class, natural-language training data is generated, which may include few-shot training data. The training process also incorporates synthetic training data generated through model inversion of the original classifier, allowing the NLP classifier to identify text across both existing and new classes.

Career Highlights

Ruiyi Zhang is currently employed at Adobe, Inc., where he continues to innovate in the field of machine learning and natural language processing. His work has been instrumental in advancing the capabilities of NLP systems, making them more robust and adaptable to new challenges.

Collaborations

Zhang has collaborated with notable colleagues, including Tong Yu and Sungchul Kim, contributing to a dynamic research environment that fosters innovation and creativity.

Conclusion

Ruiyi Zhang's contributions to natural language processing through his patents and work at Adobe, Inc. highlight his role as a leading inventor in the field. His innovative approaches to machine learning continue to shape the future of technology in significant ways.