Linguistic Versus Latent Relations for Modeling Coherent Flow in Paragraphs

作者: Eduard Hovy , Alan W Black , Dongyeop Kang , Hiroaki Hayashi

DOI:

关键词: ParagraphLanguage modelRecurrent neural networkNatural language processingRelation (database)Representation (mathematics)CoreferenceDiscourse relationStructure (mathematical logic)Computer scienceArtificial intelligence

摘要: Generating a long, coherent text such as a paragraph requires a high-level control of different levels of relations between sentences (eg, tense, coreference). We call such a …

参考文章(37)
Eduard H. Hovy, Integrating text planning and production in generation international joint conference on artificial intelligence. pp. 848- 851 ,(1985)
Silvan S. Tomkins, Script theory: differential magnification of affects. Nebraska Symposium on Motivation. Nebraska Symposium on Motivation. ,vol. 26, pp. 201- 236 ,(1978)
Donn Byrne, Teaching Writing Skills ,(1992)
Yukun Zhu, Ryan Kiros, Rich Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler, Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books international conference on computer vision. pp. 19- 27 ,(2015) , 10.1109/ICCV.2015.11
George D. Gopen, Judith A. Swan, The Science of Scientific Writing American Scientist. ,vol. 78, pp. 550- 558 ,(1990)
Ehud Reiter, Robert Dale, Building Natural Language Generation Systems ,(2000)
Cécile L. Paris, Johanna D. Moore, Planning text for advisory dialogues: capturing intentional and rhetorical information Computational Linguistics. ,vol. 19, pp. 651- 694 ,(1993)
Zhiheng Huang, Kai Yu, Wei Xu, Bidirectional LSTM-CRF Models for Sequence Tagging arXiv: Computation and Language. ,(2015)
Eduard H. Hovy, Approaches to the Planning of Coherent Text Springer, Boston, MA. pp. 83- 102 ,(1991) , 10.1007/978-1-4757-5945-7_3