Summarising As A Lever For Studying Large-Scale Discourse Structure

We are using summarising as a way of studying large-scale discours¢~ structure. Much computationally-orieuted work on disconrse structure ha.s been concerned with dialogue, rather than with 'single-source' text.. Some prop()sals haw. been made for singh~-soul'ce text e.g. l~hetorical Structure Theory (Mann ;rod Tholnpsoll 1987), I)nt al'~' open to criticism (e.g. Moore and I)olla(:k 1.q92); and singlesource work has been primarily concerned with generation ((,.g. McK~,own 1985, Maybury 1991). We believc that large-scale discourse stru('tm'[~ ha.s a crucial part to play in SUlnmarising and therefore needs to be captured in the source text representation, for use in snmmarising, regardless of its contril)ution to source interpretation itself. We have been engaged in a systematic examination of Mternative types of large-scale text structure, designed to throw light on the kinds of inlbrma.tion they make available for the text above the level of individual sentence rel)r~'sentations, and how these call be used in sumlnarising. Thus source, text interpretation will provide a source representation capturing discourse structur(" over sentences, to be exploited in a condensing transformation through which the summary representation is formed, in turn leading to the output smmnary text. This is a deliberately analytical investigation, taking a broa.d view without preconceptions. We distinguish three types of discourse information with structural implications: linguistic, dolnain, and Colmnunicativ(~, and a.r(' s,~eing what large-scale text. structures these respectively give. Thus we at'(' inv(~stigating representation types categorised as dealing with informatioll either about the linguistic properties of the source text (e.g. parallelisln), or about its domain content (e.g. class lnelnbership), or abont its COlmnunicative fimction (e.g. counterclaim). We are fill'ther, for any of these types, corlsidering two alternative forms of structnl'e that we have labelled 'bot tom-up' and 'top-down' respectively. Bottom-up structures are individually created using g(,n('ra.I ruh's