A view of the EM algorithm that justifies incremental, sparse, and other variants
Learning in graphical models
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
The order of prenominal adjectives in natural language generation
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
Class-based ordering of prenominal modifiers
ENLG '09 Proceedings of the 12th European Workshop on Natural Language Generation
Prenominal modifier ordering via multiple sequence alignment
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
A flexible approach to class-based ordering of prenominal modifiers
Empirical methods in natural language generation
Midge: generating image descriptions from computer vision detections
EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics
Beauty before age?: applying subjectivity to automatic English adjective ordering
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop
Midge: generating descriptions of images
INLG '12 Proceedings of the Seventh International Natural Language Generation Conference
| Hi-index | 0.00 |
In this paper, we argue that ordering prenominal modifiers -- typically pursued as a supervised modeling task -- is particularly well-suited to semi-supervised approaches. By relying on automatic parses to extract noun phrases, we can scale up the training data by orders of magnitude. This minimizes the predominant issue of data sparsity that has informed most previous approaches. We compare several recent approaches, and find improvements from additional training data across the board; however, none outperform a simple n-gram model.