{"title":"平衡生成文本的简洁性、可读性和显著性","authors":"Bruce Eddy, A. Cawsey","doi":"10.1109/DEXA.2002.1045904","DOIUrl":null,"url":null,"abstract":"In this paper we present an architecture for generating texts that vary in the emphasis put on conciseness, readability and the marking of particularly salient items. We abandon the traditional pipeline architecture, and use an integrated approach which makes the search for an optimum text explicit, taking into account both inter-sentential and intra-sentential features. This approach can be used in generating paragraph length texts, optimised against various criteria.","PeriodicalId":254550,"journal":{"name":"Proceedings. 13th International Workshop on Database and Expert Systems Applications","volume":"219 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2002-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Balancing conciseness, readability and salience in generated text\",\"authors\":\"Bruce Eddy, A. Cawsey\",\"doi\":\"10.1109/DEXA.2002.1045904\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper we present an architecture for generating texts that vary in the emphasis put on conciseness, readability and the marking of particularly salient items. We abandon the traditional pipeline architecture, and use an integrated approach which makes the search for an optimum text explicit, taking into account both inter-sentential and intra-sentential features. This approach can be used in generating paragraph length texts, optimised against various criteria.\",\"PeriodicalId\":254550,\"journal\":{\"name\":\"Proceedings. 13th International Workshop on Database and Expert Systems Applications\",\"volume\":\"219 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2002-09-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings. 13th International Workshop on Database and Expert Systems Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/DEXA.2002.1045904\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. 13th International Workshop on Database and Expert Systems Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DEXA.2002.1045904","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Balancing conciseness, readability and salience in generated text
In this paper we present an architecture for generating texts that vary in the emphasis put on conciseness, readability and the marking of particularly salient items. We abandon the traditional pipeline architecture, and use an integrated approach which makes the search for an optimum text explicit, taking into account both inter-sentential and intra-sentential features. This approach can be used in generating paragraph length texts, optimised against various criteria.