Lexical category based computational model of syntax acquisition

摘要

This paper presents a computational model of syntax acquisition based on lexical category from a corpus of child-directed utterances. In our proposed LEXical category based Syntax Acquisition Model (LEXSAM), the implemented algorithm represents words that have an identical backbone and similar context as their associated lexical category, and extracts syntactic construction, determined by context-sensitive statistical inference. These lexical category representations approximate the semantic input available to the child, and the lexical categories specify the meanings of clusters of words or syntactic derivations. When tested on utterances from the CHILDES corpus, our model outperforms the one without lexical category. The result shows that the children are unlikely to go through a pure syntax acquisition phase, but in a processing on which the lexical semantic knowledge affects.