This paper discusses two Hidden Markov Models (HMM) for linking linguistically motivated XTAG grammar and the automatically extracted LTAG used by MICA parser. The former grammar is a detailed LTAG enriched with feature structures. And the latter one is a huge size LTAG that due to its statistical nature is well suited to be used in statistical approaches. Lack of an efficient parser and sparseness in the supertags set are the main obstacles in using XTAG and MICA grammars respectively. The models were trained by the standard HMM training algorithm, Baum-Welch. To converge the training algorithm to a better local optimum, the initial state of the models also were estimated using two semi-supervised EM-based algorithms. The resulting accuracy of the model (about 91%) shows that the models can provide a satisfactory way for linking these grammars to share their capabilities together.