Syntactic text analysis without a dictionary

Abstract

Syntactic text analysis is a very important step of automatic text processing. The key problem is that all existing approaches are dictionary-dependent. It can be impossible to analyze all sentences because of the lack of one word in the dictionary. However even the presence of the dictionary does not resolve the phrases interpretation ambiguity. At the same time fusional languages contain enough information about the parts of speech. Particularly, the endings of nouns, adjectives, verbs and participles cannot fully indicate their case, number and face because of semantic ambiguity. Prepositions also cannot always correctly indicate the cases. This yields a variety phrase interpretation. To solving this problem sharing affixes and prepositions is proposed. However fusional languages have some disadvantages. One of this is the allowance of building phrases with random word order. It leads to increase the number of options. The paper proposes to use sentences templates with analyzed phrases for ambiguity decrease. In addition usage of affixes with prepositions for text analysis provides the basic elements of the semantic analysis without a dictionary.