Abstract Generation Based On Rhetorical Structure Extraction

generation is, like Machine Translation, one of the ultimate goal of Natural Language Processing. However, since conventional word–frequency– based abstract generation systems(e.g. [Kuhn 58]) are lacking in inter-sentential or discourse-structural analysis, they are liable to generate incoherent abstracts. On the other hand, conventional knowledge or script–based abstract generation systems(e.g. [Lehnert 80], [Fum 86]), owe their success to the limitation of the domain, and cannot be applied to document with varied subjects, such as popular scientific magazine. To realize a domain-independent abstract generation system, a computational theory for analyzing linguistic discourse structure and its practical procedure must be established. Hobbs developed a theory in which he arranged three kinds of relationships between sentences from the text coherency viewpoint [Hobbs 79]. Grosz and Sidner proposed a theory which accounted for interactions between three notions on discourse: linguistic structure, intention, and attention [Grosz et al. 86]. Litman and Allen described a model in which a discourse structure of conversation was built by recognizing a participant’s plans [Litman et al. 87]. These theories all depend on extra-linguistic knowledge, the accumulation of which presents a problem in the realization of a practical analyzer. Cohen proposed a framework for analyzing the structure of argumentative discourse [Cohen 87], yet did not provide a concrete identification procedure for ‘evidence’ relationships between sentences, where no linguistic clues indicate the relationships. Also, since only relationships between successive sentences were considered, the scope which the relationships cover cannot be analyzed, even if explicit connectives are detected. Mann and Thompson proposed a linguistic structure of text describing relationships between sentences and their relative importance [Mann et al. 87]. However, no method for extracting the relationships from superficial linguistic expressions was described in their paper. We have developed a computational model of discourse for Japanese expository writings, and implemented a practical procedure for extracting discourse structure[Sumita 92]. In our model, discourse structure is defined as the rhetorical structure, i.e., the compound of rhetorical relations between sentences in text. Abstract generation is realized as a suitable application of the extracted rhetorical structure. In this paper we describe briefly our discourse model and discuss the abstract generation system based on it.