The present disclosure relates to a text parsing system and related method for accurately parsing the content of text in messages and providing an output that can be used by various systems including systems used to detect spam and advertising content. The text parsing system can include a computing system that can parse the content of text (e.g., using a computing system including a machine-learned model or a rules based text parsing system) and provide an output including a list of potential parsed words along with associated word types, language, and confidence of word matching. Furthermore, the text parsing system can further determine the content of text through use of a knowledge base that includes a structured data repository represented as a graph. The knowledge base can be used to generate further output associated with the content of the text including related information drawn from the knowledge base.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Chen, Bokai and Guan, Xin, "Human-Style Text Parsing System", Technical Disclosure Commons, (August 14, 2018)