Summarizing News Clusters on the Basis of Thematic Chains

In this paper we consider a method for extraction of sets of semantically similar language expressions representing different participants of the text story – thematic chains. The method is based on the structural organization of news clusters and exploits comparison of various contexts of words. The word contexts are used as a basis for extracting multiword expressions and constructing thematic chains. The main difference of thematic chains in comparison with lexical chains is the basic principle of their construction: thematic chains are intended to model different participants (concrete or abstract) of the situation described in the analyzed texts, what means that elements of the same thematic chain cannot often co-occur in the same sentences of the texts under consideration. We evaluate our method on the multi-document summarization task.