DiMarco, C., Hirst, G. and Hovy, E. Generation by selection and repair as a method for adapting text for the individual reader. In: Proceedings of the Flexible Hypertext Workshop, 8th ACM International Hypertext Conference. Southampton, UK, 1997. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Refining Instructional Text Generation after Evaluation - de Rosis (Correct)
....possibility of introducing elements of empathy, emphasizing de emphasizing techniques and user tailored definitions of medical terms. We should stress here that the crucial issue is not the use of canned texts rather than Penman like surface generators: people working at the HealthDoc project [18] demonstrated that qualitatively good texts can be produced by relying almost exclusively on sentence planning techniques applied to pre authored texts. Nevertheless, their sources are, once again, set up ad hoc for the purpose of generation, whereas OPADE has to do its best with the pieces of ....
C. DiMarco, G. Hirst, and E. Hovy. Generation by Selection and Repair as a Method for Adapting Text for the Individual Reader. In Proceedings of the Workshop on Flexible Hypertext, Eighth ACM International Hypertext Conference, 1997.
Generating Natural Language Summaries from Multiple On-Line.. - Radev (1999) (24 citations) (Correct)
....or regenerated, as part of a larger textual summary. Sato and Sato [Sato and Sato, 1998] use a system that is related to language generation: it uses syntactic transformations on user questions to nd answers to 140 user problems in a database of answers to frequently asked questions. HealthDoc [DiMarco et al. 1997, Hirst et al. 1997] extracts sentences from a so called master document and generates a concise summary of the master document s full document content. To do so, HealthDoc s sentence planner also needs to perform LRR in order to remove infelicities of phrasing and lexicalization due to ....
Chrysanne DiMarco, Graeme Hirst, and Eduard Hovy. Generation by selection and repair as a method for adapting text for the individual reader. In Proceedings of the Workshop on Flexible Hypertext, 8th ACM International Hypertext Conference, Southampton, England, 1997.
Generating Natural Language Summaries from Multiple On-Line.. - Radev (1999) (24 citations) (Correct)
....or regenerated, as part of a larger textual summary. Sato and Sato [Sato and Sato, 1998] use a system that is related to language generation: it uses syntactic transformations on user questions to find answers to 140 user problems in a database of answers to frequently asked questions. HealthDoc [DiMarco et al. 1997, Hirst et al. 1997] extracts sentences from a so called master document and generates a concise summary of the master document s full document content. To do so, HealthDoc s sentence planner also needs to perform LRR in order to remove infelicities of phrasing and lexicalization due to ....
Chrysanne DiMarco, Graeme Hirst, and Eduard Hovy. Generation by selection and repair as a method for adapting text for the individual reader. In Proceedings of the Workshop on Flexible Hypertext, 8th ACM International Hypertext Conference, Southampton, England, 1997.
Component tasks in applied NLG systems - Cahill, Reape (1999) (2 citations) (Correct)
....surface realiser. Referring expression generation is not performed in any real sense, all referring expressions being always generic or proper . There is no use of centering or salience. CD SP SR Job description builder ffl ffl Job description generator ffl 3. 6 HealthDoc HealthDoc ( DHW95] DHH97] HDHP97] HW96] Par97] WH96] Wil95] is an unusual system in that it does not do generation of language from another mode, but rather selects and repairs existing text parts. The input to HealthDoc is a full natural language text, which (allegedly) contains every piece of information ....
C. DiMarco, G. Hirst, and E. Hovy. Generation by selection and repair as a method for adapting text for the individual reader. In Proceedings of the Workshop on Flexible Hypertext, 8th ACM International Hypertext Conference, Southampton, May 1997.
Lexicalisation in Applied NLG systems - Cahill (1999) (2 citations) (Correct)
....closer in form or denotation to linguistic lexical forms. Caption Generation System [MMCRng] MRM 95] MP93] Proverb [HF96] HF97] Joyce [RK] Patent Claim Expert [SN96] Exclass [CK94] Gist [Con96] PC96] Drafter [PVF 95] Drafter2 [PSE98] PS98] SPE98] HealthDoc [DHW95] [DHH97], HDHP97] PostGraphe [FL96] ModEx [LRR97] 2 Content words vs function words In the applied NLG systems in our survey, the choice of the actual words that appear in the output text may be performed at various places in various ways. Some systems include the use of canned and semi fixed text ....
C. DiMarco, G. Hirst, and E. Hovy. Generation by selection and repair as a method for adapting text for the individual reader. In Proceedings of the Workshop on Flexible Hypertext, 8th ACM International Hypertext Conference, Southampton, May 1997.
Refining Instructional Text Generation after Evaluation - de Rosis, Grasso, al. (1999) (Correct)
....possibility of introducing elements of empathy, emphasizing de emphasizing techniques and user tailored definitions of medical terms. We should stress here that the crucial issue is not the use of canned texts rather than Penman like surface generators: people working at the HealthDoc project [18] demonstrated that qualitatively good texts can be produced by relying almost exclusively on sentence planning techniques applied to pre authored texts. Nevertheless, their sources are, once again, set up ad hoc for the purpose of generation, whereas OPADE has to do its best with the pieces of ....
C. DiMarco, G. Hirst, and E. Hovy. Generation by Selection and Repair as a Method for Adapting Text for the Individual Reader. In Proceedings of the Workshop on Flexible Hypertext, Eighth ACM International Hypertext Conference, 1997.
The Rhetorical Parsing, Summarization, and Generation of Natural.. - Marcu (1997) (Correct)
....the high level communicative goal is tell everything that is in this knowledge base , the bottom up approach also enables a simple solution to the problem of generating text plans that satisfy multiple communicative goals. The bottom up text planning algorithms were incorporated into HealthDoc [ DiMarco et al. 1997, Hirst et al. 1997 ] a natural language system that generates texts that are tailored to particular audiences. Conclusions In the last chapter, I critically review the main contributions of the thesis and point to future research directions. The constraint satisfaction algorithm for ....
.... text planning . Moore and Paris, 1993, Meteer, 1992, Moore, 1995 ] and derive the set of rhetorical relations that hold between every pair of semantic units. For very rich KBs, such as that used in the HealthDoc Project [ Wanner and Hovy, 1996, Hovy and Wanner, 1996, DiMarco and Foster, 1997, DiMarco et al. 1997, Hirst et al. 1997 ] one can simply extract these relations directly, because they are explicitly represented. Each of the alternatives described above has been already discussed in the literature to a greater or lesser extent. Therefore, for the purpose of this thesis, I will simply assume ....
[Article contains additional citation context not shown here]
Chrysanne DiMarco, Graeme Hirst, and Eduard Hovy. Generation by selection and repair as a method for adapting text for the individual reader. In Proceedings of the Workshop on Flexible Hypertext, Eighth ACM International Hypertext Conference, Southampton, UK, April 1997.
Con-Textual Navigation Support - Geldof (Correct)
No context found.
DiMarco, C., Hirst, G. and Hovy, E. Generation by selection and repair as a method for adapting text for the individual reader. In: Proceedings of the Flexible Hypertext Workshop, 8th ACM International Hypertext Conference. Southampton, UK, 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC