Three new probabilistic models for dependency parsing: an exploration
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
Incremental parsing with the perceptron algorithm
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Online Passive-Aggressive Algorithms
The Journal of Machine Learning Research
Broad coverage multilingual deep sentence generation with a stochastic multi-level realizer
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Minimal dependency length in realization ranking
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Generating non-projective word order in statistical linearization
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Towards a surface realization-oriented corpus annotation
INLG '12 Proceedings of the Seventh International Natural Language Generation Conference
| Hi-index | 0.00 |
We realize the full generation pipeline, from the deep (= semantic) representation (SemR), over the shallow (= surface-syntactic) representation (SSyntR) to the surface. To account systematically for the non-isomorphic projection between SemR and SSyntR, we introduce an intermediate representation: the so-called deep-syntactic representation (DSyntR), which does not contain yet (all) function words (as SemR), but which already contains grammatical function relation labels (as SSyntR).