Summary: Parsing By Chunks
Steven P. Abney
Bell Communications Research
I begin with an intuition: when I read a sentence, I read it a chunk at a time. For example, the
previous sentence breaks up something like this:
(1) [I begin] [with an intuition]: [when I read] [a sentence], [I read it] [a chunk] [at a
These chunks correspond in some way to prosodic patterns. It appears, for instance, that the
strongest stresses in the sentence fall one to a chunk, and pauses are most likely to fall between
chunks. Chunks also represent a grammatical watershed of sorts. The typical chunk consists of a
single content word surrounded by a constellation of function words, matching a fixed template.
A simple context-free grammar is quite adequate to describe the structure of chunks. By contrast,
the relationships between chunks are mediated more by lexical selection than by rigid templates.
Co-occurence of chunks is determined not just by their syntactic categories, but is sensitive to the
precise words that head them; and the order in which chunks occur is much more flexible than the
order of words within chunks.
The work I would like to describe is an attempt to give content to these intuitions, and to show
that parsing by chunks has distinct processing advantages, advantages that help explain why the
human parser might adopt a chunk-by-chunk strategy.