Coupling CCG and hybrid logic dependency semantics
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Semiotic schemas: a framework for grounding language in action and perception
Artificial Intelligence - Special volume on connecting language to the world
Log-linear models for wide-coverage CCG parsing
EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
New developments in parsing technology
Incremental parsing with the perceptron algorithm
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Incremental natural language processing for HRI
Proceedings of the ACM/IEEE international conference on Human-robot interaction
Crossmodal content binding in information-processing architectures
Proceedings of the 3rd ACM/IEEE international conference on Human robot interaction
Salience-driven Contextual Priming of Speech Recognition for Human-Robot Interaction
Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
Towards an integrated robot with multiple cognitive functions
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
High efficiency realization for a wide-coverage unification grammar
IJCNLP'05 Proceedings of the Second international joint conference on Natural Language Processing
Tutor-based learning of visual categories using different levels of supervision
Computer Vision and Image Understanding
Hi-index | 0.00 |
Spoken dialogue is notoriously hard to process with standard NLP technologies. Natural spoken dialogue is replete with disfluent, partial, elided or ungrammatical utterances, all of which are very hard to accommodate in a dialogue system. Furthermore, speech recognition is known to be a highly error-prone task, especially for complex, open-ended discourse domains. The combination of these two problems -- ill-formed and/or misrecognised speech inputs -- raises a major challenge to the development of robust dialogue systems. We present an integrated approach for addressing these two issues, based on a incremental parser for Combinatory Categorial Grammar. The parser takes word lattices as input and is able to handle illformed and misrecognised utterances by selectively relaxing its set of grammatical rules. The choice of the most relevant interpretation is then realised via a discriminative model augmented with contextual information. The approach is fully implemented in a dialogue system for autonomous robots. Evaluation results on a Wizard of Oz test suite demonstrate very significant improvements in accuracy and robustness compared to the baseline.