Neural models for key phrase detection and question generation

• Main Authors: Subramanian, Sandeep, Yuan, Xingdi, Wang, Tong, Trischler, Adam Peter
• Format: Patent
• Language: English
• Published: 17.09.2024
• Subjects: ADVERTISING; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND,DEAF OR MUTE; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; CRYPTOGRAPHY; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; DIAGRAMS; DISPLAY; EDUCATION; EDUCATIONAL OR DEMONSTRATION APPLIANCES; GLOBES; PHYSICS; PLANETARIA; SEALS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

A method, system, and storage device storing a computer program, for generating questions based on provided content, such as, for example, a document having words. The method comprises automatically estimating the probability of interesting phrases in the provided content, and generating a question in natural language based on the estimating. In one example embodiment herein, the estimating includes predicting the interesting phrases as answers, and the estimating is performed by a neural model. The method further comprises conditioning a question generation model based on the interesting phrases predicted in the predicting, the question generation model generating the question. The method also can include training the neural model. In one example, the method further comprises identifying start and end locations of the phrases in the provided content, and the identifying includes performing a dot product attention mechanism parameterizing a probability distribution.