The goal of the Alignment-Based Learning (ABL) grammatical
inference framework is to structure plain (natural language)
sentences as if they are parsed according to a context-free
grammar. The framework produces good results even when 
simple techniques are used. However, the techniques used so
far have computational drawbacks, resulting in limitations
with respect to the amount of language data to be used. In
this article, we propose a new alignment method, which can
find possible constituents in time linear in the amount of
data. This solves the scalability problem and allows ABL to
be applied to larger data sets.