Meta-Discourse Markers And Problem-Structuring In Scientific Articles

Knowledge about the argumentative structure of scientific articles can, amongst other things, be used to improve automatic abstracts. We argue that the argumentative structure of scientific discourse can be automatically detected because reasordng about problems, research tasks and solutions follows predictable patterns. Certain phrases explicitly mark the rhetorical status (communicative function) of sentences with respect to the global argumentative goal. Examples for such meta-diacaurse markers are "in this paper, we have p r e s e n t e d . . . " or "however, their method fails to". We report on work in progress about recognizing such meta-comments automatically in research articles from two disciplines: computational linguistics and medicine (cardiology). 1 M o t i v a t i o n We are interested in a formal description of the document s t ructure of scientific articles from different disciplines. Such a description could be of practical use for many applications in document management; our specific mot ivat ion for detecting document structure is qual i ty improvement in automatic abstracting. Researchem in the field of automatic abstracting largely agree that it is currently not technically feasible to create automatic abstracts based on full text unders tanding (Sparck Jones 1994). As a result, many researchers have turned to sentence extraction (Kupiec, Pedersen, & Chen 1995; Brandow, Mitze, & Rau 1995; Hovy & Lin 1997). Sentence extraction, which does not involve any deep analysis, has the huge advantage of being robust with respect to individual writing style, discipline and text type (genre). Instead of producing a b s t r a c t , this results produces only extracts: documen t surrogates consisting of a number of sentences selected verbat im from the original text. We consider a concrete document retrieval (DR) scenario in which a researcher wants to select one or more scientific articles from a large scientific database (or even f rom the Internet) for further inspection. The ma in task for the searcher is relevance decision for each paper: she needs to decide whether or not to spend more t ime on a paper (read or skim-read it), depending on how useful it presumably is to her current information needs. Traditional sentence extracts can be used as rough-and-ready relevance indicators for this task, but they are not doing a great job at representing the contents of the original document: searchers often get the wrong idea about what the text is about. Much of this has to do with the fact that extracts are typically incoherent texts, consisting of potential ly unrelated sentences which have been taken out of their context. Crucially, extracts have no handle at revealing the text 's logical and semantic organisation. More sophisticated, user-tailored abstracts could help the searcher make a fast, informed relevance decision by taking factors like the searcher's expertise and current information need into account. If the searcher is dealing with research she knows well, her information needs might be quite concrete: during the process of writing her own paper she might want to find research which supports her own claims, find out if there are contradictory results to hers in the literature, or compare her results to those of researchers using a similar methodology. A different information need arises when she wants to gain an overview of a new research area as an only "partially informed user" in this field (Kircz 1991) she will need to find out about specific research goals, the names of the researchers who have contributed the main research ideas in a given time period, along with information of methodology and results in this research field. There are new functions these abstracts could fulfil. In order to make an informed relevance decision, the searcher needs to judge differences and similarities between papers, e.g. how a given paper relates to similar papers with respect to research goals or methodology, so that she can place the research described in a given paper in the larger picture of the field, a function we call navigation between research articles. A similar operation is navigation within a paper, which supports searchers in non-linear reading and allows them to find relevant information faster, e.g. numerical results. We believe that a document surrogate that aims at supporting such functions should characterize research articles in terms of the problems, research tasks and