Regina Barzilay and Mirella Lapata. 2005. Collective Content Selection for Concept-To-Text Generation. In Proceedings of the Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing, 331-338. Vancouver. A content selection component determines which information should be conveyed in the output of a natural language generation system. We present an ef - cient method for automatically learning content selection rules from a corpus and its related database. Our modeling framework treats content selection as a collective classi cation problem, thus allowing us to capture contextual dependencies between input items. Experiments in a sports domain demonstrate that this approach achieves a substantial improvement over context-agnostic methods.
@InProceedings{Barzilay:Lapata:05b, author = {Regina Barzilay and Mirella Lapata}, title = {Collective Content Selection for Concept-To-Text Generation}, crossref = {EMNLP:05}, pages = {331--338} } @Proceedings{EMNLP:05, title = {Proceedings of the HLT/EMNLP}, booktitle = {Proceedings of the HLT/EMNLP}, address = {Vancouver}, year = 2005 } |