An unsupervised approach to recognizing discourse relations
作者： Daniel Marcu , Abdessamad Echihabi
关键词: Contrast (music) 、 Linguistics 、 Natural language processing 、 Natural language 、 Discourse connectives 、 Computer science 、 Elaboration 、 Semantics 、 Computational linguistics 、 Artificial intelligence 、 Discourse relation
摘要: We present an unsupervised approach to recognizing discourse relations of CONTRAST, EXPLANATION-EVIDENCE, CONDITION and ELABORATION that hold between arbitrary spans texts. show relation classifiers trained on examples are automatically extracted from massive amounts text can be used distinguish some these with accuracies as high 93%, even when the not explicitly marked by cue phrases.
aclweb.org
acm.org
isi.edu 参考文章(14)
Chris Mellish, Jon Oberlander, Alistair Knott, Michael O'Donnell, Beyond Elaboration: The Interaction of Relations and Focus in Coherent Text John Benjamins. pp. 181- 196 ,(2000)
Jerry R. Hobbs, Literature and cognition ,(1990)
Eduard H. Hovy, Elisabeth Maier, Parsimonious or Profligate: How Many and Which Discourse Structure Relations? Defense Technical Information Center. ,(1992) , 10.21236/ADA278715
J.R. Martin, English Text: System and structure ,(1992)
Eugene Charniak, A maximum-entropy-inspired parser north american chapter of the association for computational linguistics. pp. 132- 139 ,(2000)
Christopher D. Manning, Hinrich Schütze, Foundations of Statistical Natural Language Processing ,(1999)
Daniel Marcu, The Theory and Practice of Discourse Parsing and Summarization ,(2000)
Alistair Knott, Ted Sanders, The classification of coherence relations and their linguistic markers: An exploration of two languages Journal of Pragmatics. ,vol. 30, pp. 135- 175 ,(1998) , 10.1016/S0378-2166(98)00023-X
Alex Lascarides, Nicholas Asher, Temporal interpretation, discourse relations and commonsense entailment Linguistics and Philosophy. ,vol. 16, pp. 437- 493 ,(1993) , 10.1007/BF00986208
M. A. K. Halliday, Ruqaiya Hasan, Cohesion in English ,(1976)