Method of using open-domain information for understanding context of temporal relation information
AssigneeKorea Advanced Institute of Science and Technology
InventorsHo Jin CHOI, Chae Gyun LIM
Life of this patent
Estimating the term…
Loading patent…
AssigneeKorea Advanced Institute of Science and Technology
InventorsHo Jin CHOI, Chae Gyun LIM
Estimating the term…
A method of using open domain information for understanding a context of temporal relation information is implemented as a computer program and performed using a computing device. Unnecessary elements is removed by data pre-processing from an input text in a natural language, and then linguistic characteristics of the pre-processed input text are analyzed to generate a linguistic analysis result in a structure form. Candidates for temporal relation information included in the input text are generated by analyzing temporal information and open domain information included in the input text using the linguistic analysis result, then validity of the candidates is verified to generate verified temporal relation information. Since the temporal relation information can be grasped based on the open-domain information in the input text, quality and accuracy of an information extraction result can be increased in applications, thereby improving system performance for question and answer, document summary, conversation systems, etc.
A method of using open domain information for understanding a context of temporal relation information, performed using a computing device comprising at least a processor and a memory element, and the method comprising:
Dependencies are inferred from the claim text.