Text generation: using discourse strategies and focus constraints to generate natural language text
Text generation: using discourse strategies and focus constraints to generate natural language text
Automated discourse generation using discourse structure relations
Artificial Intelligence - Special volume on natural language processing
Empirically designing and evaluating a new revision-based model for summary generation
Artificial Intelligence - Special volume on empirical methods
Negotiation for automated generation of temporal multimedia presentations
MULTIMEDIA '96 Proceedings of the fourth ACM international conference on Multimedia
Building natural language generation systems
Building natural language generation systems
Generating referring expressions in a domain of objects and processes (language representation)
Generating referring expressions in a domain of objects and processes (language representation)
Planning text for advisory dialogues: capturing intentional and rhetorical information
Computational Linguistics
Language generation for multimedia healthcare briefings
ANLC '97 Proceedings of the fifth conference on Applied natural language processing
A portable algorithm for mapping bitext correspondence
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
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
Sentence ordering in multidocument summarization
HLT '01 Proceedings of the first international conference on Human language technology research
Description of the UMass system as used for MUC-6
MUC6 '95 Proceedings of the 6th conference on Message understanding
Can text structure be incompatible with rhetorical structure?
INLG '00 Proceedings of the first international conference on Natural language generation - Volume 14
Automatic Evaluation of Information Ordering: Kendall's Tau
Computational Linguistics
Acquiring correct knowledge for natural language generation
Journal of Artificial Intelligence Research
Learning content selection rules for generating object descriptions in dialogue
Journal of Artificial Intelligence Research
Inferring strategies for sentence ordering in multidocument news summarization
Journal of Artificial Intelligence Research
A bottom-up approach to sentence ordering for multi-document summarization
Information Processing and Management: an International Journal
Reuse and challenges in evaluating language generation systems: position paper
Evalinitiatives '03 Proceedings of the EACL 2003 Workshop on Evaluation Initiatives in Natural Language Processing: are evaluation methods, metrics and resources reusable?
Optimising natural language generation decision making for situated dialogue
SIGDIAL '11 Proceedings of the SIGDIAL 2011 Conference
A preference learning approach to sentence ordering for multi-document summarization
Information Sciences: an International Journal
Generating natural language descriptions from OWL ontologies: the natural OWL system
Journal of Artificial Intelligence Research
Hi-index | 0.00 |
In a language generation system, a content planner embodies one or more "plans" that are usually hand--crafted, sometimes through manual analysis of target text. In this paper, we present a system that we developed to automatically learn elements of a plan and the ordering constraints among them. As training data, we use semantically annotated transcripts of domain experts performing the task our system is designed to mimic. Given the large degree of variation in the spoken language of the transcripts, we developed a novel algorithm to find parallels between transcripts based on techniques used in computational genomics. Our proposed methodology was evaluated two--fold: the learning and generalization capabilities were quantitatively evaluated using cross validation obtaining a level of accuracy of 89%. A qualitative evaluation is also provided.