Modelagem de discurso para o tratamento da concisão e preservação da idéia central na geração de textos

Summary writing strategies based on discourse structures, relevance theory and kernel preservation

“…As an example, the headline in Example I excluded the cause of the accident-the icy road; although important enough for the lead sentence, this information was regarded as not important enough to cram into the headline. This approach is in line with the structure-based deletion heuristics developed by Rino andScott (1994, 1996) for computer summarization, which are discussed later. For the more general case of descriptive writing, where the semantic boundaries and types of information are less clear, we will have to use other more subjective criteria.…”

“…That the essence is the central feature of a story is apparent in Rino's (1996) use of Ideia Central in the title of her major work. Her term esqueleto bdsico encapsulates the "content+ structure" meaning of"gist;' but she defines this as a proposifiiO central de um discurso (p. 27), defined in Rino and Scott (1996) as: "The central proposition.…”

“…These views are not inconsistent, as the former involves the kernel, whereas the latter involves the gist. The need to preserve the central feature of an original in a summary is central to Rino's (1996) work on the Preservarao de Ideia Central na Gerarao de Textos.…”

Finding related sentences in multiple documents for multidocument discourse parsing of Brazilian Portuguese texts

“…In the beginning of the 80's emerged one of the most used discourse theories, RST (Rhetorical Structure Theory) [10], which is largely used until today. This theory identifies relations between parts of a text (e.g., cause-effect, contrast, and elaboration relations) and, with the existence of many RST discourse parsers, the theory helped many applications of Natural Language Processing (NLP) such as summarization ( [11][13] [15], text generation [19], essay scoring [3] and others.…”

On the Development and Evaluation of a Brazilian Portuguese Discourse Parser

“…The ability to automatically derive discourse structures of texts is of great importance to many applications in Computational Linguistics. For instance, it may be very useful for identifying relevant information of a text to produce its summary (see, for instance, [23][32] [38]), determining the possible antecedent text spans for a referred term in coreference resolution [8] [44], producing coherent texts according to communicative goals in text generation [28][29] [42], adequately rearranging spans of texts being translated in a machine translation task [25], identifying missing important components in a essay scoring procedure [4], elaborating an answer to better satisfy an specific user in a question answering system [3], among other natural language applications.…”