Predicting Garden Path Sentences Based on Natural Language Understanding System

Abstract — Natural language understanding (NLU) focusing on machine reading comprehension is a branch of natural language processing (NLP). The domain of the developing NLU system covers from sentence decoding to text understanding and the automatic decoding of GP sentence belongs to the domain of NLU system. GP sentence is a special linguistic phenomenon in which processing breakdown and backtracking are two key features. If the syntax-based system can present the special features of GP sentence and decode GP sentence completely and perfectly, NLU system can improve the effectiveness and develop the understanding skill greatly. On the one hand, by means of showing Octav Popescu’s model of NLU system, we argue that the emphasis on the integration of syntactic, semantic and cognitive backgrounds in system is necessary. On the other hand, we focus on the programming skill of IF-THEN-ELSE statement used in N-S flowchart and highlight the function of context free grammar (CFG) created to decode GP sentence. On the basis of example-based analysis, we reach the conclusion that syntax-based machine comprehension is technically feasible and semantically acceptable, and that N-S flowchart and CFG can help NLU system present the decoding procedure of GP sentence successfully. In short, syntax-based NLU system can bring a deeper understanding of GP sentence and thus paves the way for further development of syntax-based natural language processing and artificial intelligence. Keywords- Natural language understanding; N-S flowchart; computational linguistics; context free grammar; garden path sentences. I