UNSUPERVISED LEARNING OF DEEP PATTERNS FOR SEMANTIC PARSING

• Main Authors: KIMELFELD BENNY, VAITHYANATHAN SHIVAKUMAR
• Format: Patent
• Language: English
• Published: 19.02.2015
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

Using exemplary sentences, usage patterns and thematic roles ascribed in VerbNet to generate "deep pattern trees" for the exemplary sentences. Then, when an arbitrary natural language subject sentence is input, these deep pattern trees can be matched to the natural language subject sentenc...