Abstract Generation Based on Rhetorical Structure Extraction

ABSTRACT GENERATION BASED ON RHETORICAL STRUCTURE EXTRACTION Kenjl Ono, Kazuo Sumlta, Seijl Miike Research and Development Center Toshiba Corporation Komukai-Toshiba-cho 1, Saiwai-ku, Kawmsaki, 210, Japan ono@isl.rdc.toshiba.co.jp 1 ABSTRACT We have developed an automatic abstr~mt genera- tion system for Japanese expository writings based on rhetorical structure extraction. The system first extracts the rhetorical structure, the compound of the rhetorical relations between sentences, and then cuts out less important parts in the extracted struc- ture to generate an abstract of the desired length. Evaluation of the generated abstract showed that it contains at maximum 74% of the most important sentences of the original text. The system is now utilized as a text browser for a prototypicaI interac- tive document retrieval system. 2 INTRODUCTION Abstract generation is, like Machine Translation, one of the ultimate goal of Natural Language Process- ing. IIowever, 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 ab- stracts. On the other hand, conventional knowl- edge or script-based abstract generation systems(e.g. [behnert 801, [Fum 86]), owe their success to the li,n- itation of the domain, and cannot be applied to doc- ument with varied subjects, such ,as popular scientific magazine. To realize a domain-independent abstract generation system, a computational theory for ana- lyzing linguistic discourse structure and its practical procedure must be established. ltobbs developed a theory in which lie arranged three kinds of relationships between sentences from the text coherency viewpoint [Hobbs 79]. Grosz and Sidner proposed a theory which ac- counted for interactions between three notions on discourse: linguistic structure, intention, and atten- tion [C, rosz et al. 86]. l,itman and Allen described a model in which a discourse structure of conversation was built by recognizing a participanUs plans [Litman et al. 87]. 'l'hese theories all depend on extra-linguistic knowl- edge, 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 provkle 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. Mama and Thompson proposed a linguistic struc- ture of text describing relationships between sen- tences and their relative importance [Mann et al. 87]. llowever, no method for extracting the relationships from superficial linguistic expressions was described in their paper. We have developed a computational rnodel of discourse for Japanese expository writings, and im- plemented a practical procedure for extracting dis- course structure[Sumita 92]. In our model, discourse structure is deiined ,as the rhetorical structure, i.e., the compound of rhetorical relations between sen- tences in text. Abstr~t generation is realized ~s a suitaMe application of the extracted rhetorical struc- ture. In this paper we describe briefly our discourse model and discuss the abstract generation system based on it. 344 3 RHETORICAl, STRUCTURE Rhetorical structure …

Content truncated to 500 words