Machine Learning for Second Language Learning: Effects on Syntactic Processing in Garden-Path Sentences

With the rapid development of educational technologies, machine learning (ML) based second language learning (SLL) attracts the attention of many scholars from computational linguistics. Garden path (GP) sentence is a special sentence structure in which processing breakdown and backtracking are involved in the machine decoding. Faced with GP sentence, learners have to make original misinterpretation linger even after reanalysis has occurred, and have to face the fact that initial interpretations of GP sentence are often incorrect and do not correspond to the final output. On the basis of computational skills of N-S flowchart, recursive transition network, and well-formed substring table, this paper highlights the effects on syntactic processing in garden-path sentences when context-free grammar (CFG) driven ML system is introduced. There are two main conclusions to be drawn from the above discussion. Firstly, CFG-driven ML system can help SLL learners better understand the GP sentences in second language even no rich lingual environment is provided. Secondly, the hybrid knowledge, e.g. grammatical, cognitive and semantic information, needs to be integrated into ML system to help SLL learners achieve the "good enough" results in decoding GP sentences.