Tree Database

The Tree Database contains the tree templates that are lexicalized by following the various steps given above. The lexical items are inserted into distinguished nodes in the tree template called the anchor nodes. The part of speech of each word in the sentence corresponds to the label of the anchor node of the trees. Hence the tagset used by the POS Tagger corresponds exactly to the labels of the anchor nodes in the trees. The tagset used in the XTAG system is given in Table 3.3. The tree templates are subdivided into tree families (for verbs and other predicates), and tree files which are simply collections of trees for lexical items like prepositions, determiners, etc ^3.2 .