... "+wa" in Table 1. Thus there are seven secondary targets: niwa, karawa, towa, dewa, ewa, madewa, yoriwa. Therefore, we have in total 18 case particles to assign to phrases. 2.2 Task ... taking advantage of the fact that language models do not require dependency annotation for training. The language models were trained using the CMU language modeling toolkit with default parame-ter ... words aligned to the head of the phrase, to the head of the parent phrase, or to any alterative parents. If any word in the phrase is aligned to a preposition in the source language, our model...