[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

[ Back to the navigation ]

You are here: start » mckeown_abstract

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
mckeown_abstract [2012/11/08 13:52]
ufal 		mckeown_abstract [2012/12/23 09:41]
ufal
Line 1: Line 1:
 **Kathleen McKeown, Columbia University** **Kathleen McKeown, Columbia University**
 //Penn Discourse Treebank Relations and their Potential for Language Generation// //Penn Discourse Treebank Relations and their Potential for Language Generation//
 +
 +({{:coling_2012_adaca_pdtb_mckeown.pdf|presentation}})
  
 In the early eighties, language generation researchers explored the use of rhetorical relations, in the form of schemata or common patterns of rhetorical structure (McKeown 85) and later in the form of rhetorical structure theory (RST) (Mann 84).  Researchers in language generation showed how discourse structure could be used to plan the content of a text (McKeown 85, Moore and Paris 93, Hovy 88). In most cases, structure was linked in some way to content, whether directly or through planning how to satisfy speaker intentions, and this was critical to the success of using discourse structure for content planning. Later work (Barzilay 2010, Barzilay and Lapata 2005) took a modern approach to this problem, developing techniques to learn common discourse structures for specific domains and using these learned discourse structures to control content selection and organization.  In the early eighties, language generation researchers explored the use of rhetorical relations, in the form of schemata or common patterns of rhetorical structure (McKeown 85) and later in the form of rhetorical structure theory (RST) (Mann 84).  Researchers in language generation showed how discourse structure could be used to plan the content of a text (McKeown 85, Moore and Paris 93, Hovy 88). In most cases, structure was linked in some way to content, whether directly or through planning how to satisfy speaker intentions, and this was critical to the success of using discourse structure for content planning. Later work (Barzilay 2010, Barzilay and Lapata 2005) took a modern approach to this problem, developing techniques to learn common discourse structures for specific domains and using these learned discourse structures to control content selection and organization. 
Line 9: Line 11:
  
 In language generation, discourse structure relations often play a prescriptive role in determining what to say next. If content has already been selected, that content in conjunction with discourse structure can be used to constrain what gets said next. PDTB relations have been empirically determined through analysis of text and there has been an effort to limit the range of relations. One natural question is whether PDTB relations should serve the same role as RST in generating of text or whether there is a difference in how they could be applied.  Could the specific annotation of senses associated with relations be used to help determine content? There is an aspect of the PDTB which differs from earlier work on RST as it ties in closer to the syntactic structure of the text. Could the close coupling of discourse structure, syntactic structure and sense annotation offer an advantage over previous methods? One possibility would be to explore the role it could play in sentence planning, the problem of determining how to combine simple propositions to generate more complex sentences. In language generation, discourse structure relations often play a prescriptive role in determining what to say next. If content has already been selected, that content in conjunction with discourse structure can be used to constrain what gets said next. PDTB relations have been empirically determined through analysis of text and there has been an effort to limit the range of relations. One natural question is whether PDTB relations should serve the same role as RST in generating of text or whether there is a difference in how they could be applied.  Could the specific annotation of senses associated with relations be used to help determine content? There is an aspect of the PDTB which differs from earlier work on RST as it ties in closer to the syntactic structure of the text. Could the close coupling of discourse structure, syntactic structure and sense annotation offer an advantage over previous methods? One possibility would be to explore the role it could play in sentence planning, the problem of determining how to combine simple propositions to generate more complex sentences.
 +
  
 Regina Barzilay. 2010. Probabilistic Approaches for Modeling Text Structure and Their Application to Text-to-Text Generation. In Emiel Krahmer and Mariet Theune, editors, Empirical Methods in Natural Language Generation: Data-oriented Methods and Empirical Evaluation, Springer, 2010.  Regina Barzilay. 2010. Probabilistic Approaches for Modeling Text Structure and Their Application to Text-to-Text Generation. In Emiel Krahmer and Mariet Theune, editors, Empirical Methods in Natural Language Generation: Data-oriented Methods and Empirical Evaluation, Springer, 2010. 

[ Back to the navigation ] [ Back to the content ]