The Swedish cue word men 'but' can mark the boundary between both different
topic units as well as topic-internal units in spontaneous speech. The goa
l of this study is to see if these two functions of men can be distinguishe
d on the basis of their local prosodic correlates and co-occurring lexical
items. Men-tokens in spontaneous narrations were labelled as to their funct
ion, first using text-only data. The 'strong' tokens (categorized identical
ly by all labellers) were subsequently seen to be clearly differentiated in
to two classes on the basis of related prosodic parameters and co-occurring
lexical items. This distinction was, however, not found fur the correspond
ing 'weak' tokens which were subsequently relabelled using both text and sp
eech nor for the data-base as a whole. A test using a neural network traine
d using strong tokens was seen to be able to correctly categorize 90% of th
e strong men-tokens as to their associated boundary-type (topic-shift vs. t
opic-internal). The results show that cue words along with their prosodic c
orrelates and co-occurring lexical items constitute a constellation of impo
rtant information for understanding how segmentation of spoken discourse is
produced and understood. (C) 2001 Elsevier Science B.V. All rights reserve
d.