Jiacheng Xu

Title: Innovations by Jiacheng Xu in Neural Text Generation

Introduction

Jiacheng Xu is an accomplished inventor based in Sunnyvale, California. He has made significant contributions to the field of natural language processing, particularly in the area of text generation models. His innovative work has led to the development of a unique patent that enhances the capabilities of neural text generation systems.

Latest Patents

Jiacheng Xu holds a patent for "Systems and methods for search based neural text generation models." This patent describes systems and methods for text generation using a natural language processing model. The process involves receiving natural language input, which is then encoded by an encoder. A decoder generates a plurality of next-node probabilities for a set of candidate nodes that are next to at least one of K previously decoded paths of nodes on a directed search graph. Scores are computed for each of the candidate nodes in parallel among the K previously decoded paths. The highest scoring K nodes are selected for addition to the directed search graph, and the search continues until a search budget is exhausted. The generated sequences can represent a plurality of sentences or questions, depending on the task.

Career Highlights

Jiacheng Xu is currently employed at Salesforce, Inc., where he continues to push the boundaries of innovation in technology. His work at Salesforce has allowed him to collaborate with other talented professionals in the field, further enhancing his contributions to the industry.

Collaborations

One of his notable coworkers is Yingbo Zhou, with whom he has likely shared insights and expertise in their respective projects.

Conclusion

Jiacheng Xu's innovative work in neural text generation exemplifies the advancements being made in natural language processing. His patent reflects a significant step forward in the development of intelligent text generation systems.