Company Filing History:
Years Active: 2025
Title: Innovations of Zhitao Ying in Sentiment Classification and Knowledge Graphs
Introduction
Zhitao Ying is an accomplished inventor based in Palo Alto, California. He has made significant contributions to the fields of sentiment classification and knowledge graph completion. With a total of two patents to his name, Ying's work focuses on advanced computational methods that enhance the understanding of natural language processing.
Latest Patents
Zhitao Ying's latest patents include a "Method and system for aspect-level sentiment classification by merging graphs" and a "Method and system for relation learning by multi-hop attention graph neural network." The first patent describes a system that utilizes a computing device equipped with a processor and storage device. This system is designed to receive an aspect term-sentence pair, embed it, and parse the sentence using multiple parsers to create dependency trees. It then performs edge union to obtain a merged graph and combines this with the embedding to create a relation graph. The system employs a relation graph neural network to extract hidden representations and classify the aspect term based on these representations. During training, it calculates a loss function to adjust model parameters.
The second patent focuses on completing knowledge graphs. It involves a computing device that processes an incomplete knowledge graph with multiple nodes and edges. The system calculates an attention matrix based on one-hop attention between connected nodes and computes multi-head diffusion attention. This process updates the embedding of the incomplete knowledge graph, resulting in an updated knowledge graph.
Career Highlights
Zhitao Ying has worked with notable companies such as Beijing Wodong Tianjun Information Technology Co., Ltd. and JD.com American Technologies Corporation. His experience in these organizations has contributed to his expertise in developing innovative solutions in technology.
Collaborations
Zhitao Ying has collaborated with professionals like Guangtao Wang and Jing Huang, enhancing his research and development efforts in the field.
Conclusion
Zhitao Ying's contributions to sentiment classification and knowledge graph completion demonstrate his innovative spirit and technical expertise. His patents reflect a commitment to advancing computational methods in natural language processing.