Although indexes may overlap, the output of an automatic indexer is generally presented as a fiat and unstructured list of terms. Our purpose is to exploit term overlap and embedding so as to yield a substantial qualitative and quantitative improvement in automatic indexing through concept combination. The increase in the volume of indexing is for free indexing and for controlled indexing. The resulting structure of the indexed corpus is a partial conceptual analysis. 1 Overview The method, proposed here for improving automatic indexing, builds partial syntactic structures by combining overlapping indexes. .
