Knowledge representation: logical, philosophical and computational foundations
Knowledge representation: logical, philosophical and computational foundations
Generation that exploits corpus-based statistical knowledge
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Two-level, many-paths generation
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Exploiting a probabilistic hierarchical model for generation
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
The Proposition Bank: An Annotated Corpus of Semantic Roles
Computational Linguistics
Trainable sentence planning for complex information presentation in spoken dialog systems
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies
CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Stochastic language generation for spoken dialogue systems
ConversationalSys '00 Proceedings of the ANLP-NAACL 2000 Workshop on Conversational Systems
Phrase-based statistical language generation using graphical models and active learning
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Broad coverage multilingual deep sentence generation with a stochastic multi-level realizer
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
A high-performance syntactic and semantic dependency parser
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations
The first surface realisation shared task: overview and evaluation results
ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
: from deep representation to surface
ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
| Hi-index | 0.00 |
Until recently, deep stochastic surface realization has been hindered by the lack of semantically annotated corpora. This is about to change. Such corpora are increasingly available, e.g., in the context of CoNLL shared tasks. However, recent experiments with CoNLL 2009 corpora show that these popular resources, which serve well for other applications, may not do so for generation. The attempts to adapt them for generation resulted so far in a better performance of the realizers, but not yet in a genuinely semantic generation-oriented annotation schema. Our goal is to initiate a debate on how a generation suitable annotation schema should be defined. We define some general principles of a semantic generation-oriented annotation and propose an annotation schema that is based on these principles. Experiments shows that making the semantic corpora comply with the suggested principles does not need to have a negative impact on the quality of the stochastic generators trained on them.