General consensus in linguistics is that language context (or ''co-text'') plays crucial role in describing linguistic properties of language items. Isolated units are, as a corollary to this statement, inherently ambiguous (polysemous and/or polyfunctional). In this paper we describe the most influential forces leading to disambiguation of language units, specifically the role of n-gram length on its ambiguity.
The most influential achievement of corpus linguistics lies in the growing importance of context in the description of language. This is also reflected by context analysis which is introduced in this paper. Context analysis is an umbrella term for a bundle of methods sharing the same hypothesis: that all the features (form, meaning, function) of the language phenomena are mirrored by the context which they enter. It is important to emphasise that by the term ''context'', it is meant here not only one or two adjacent tokens in a particular text, but all the neighbouring units (e.g. words, lemmas, part of speech tags etc.) which co-occur with a given word in all of its instances in a corpus. The paper discusses various types of context (range, type of contextual units etc.) and their effect on the analysis. By comparing contexts of distinct words or word groups we may find out what the similarities and differences are between language units, phenomena or even groups of lexemes. This type of research was conducted here to determine the relations between parts of speech.