%0 Book %1 LemonPietquin2012 %C New York %D 2012 %E Lemon, Oliver %E Pietquin, Olivier %I Springer %K 01801 103 springer book numerical ai adaptive language processing analysis generation dialog user interface interaction learn zzz.sds %R 10.1007/978-1-4614-4803-7 %T Data-Driven Methods for Adaptive Spoken Dialogue Systems: Computational Learning for Conversational Interfaces %X The EC FP7 project 'Computational Learning in Adaptive Systems for Spoken Conversation' (CLASSiC) was a European initiative working on a fully data-driven architecture for the development of conversational interfaces, as well as new machine learning approaches for their sub-components. It developed a variety of novel statistical methods for spoken dialogue processing, for extended conversational interaction, which are now collected together in this book. A major focus of the project was in tracking the accumulation of information about user goals over multiple dialogue turns (i.e. extended conversational interaction), and in maintaining overall system robustness even when speech recognition results contain errors, by managing uncertainty through the processing chain. Other advances were made in the areas of adaptive natural language generation (NLG), statistical methods for spoken language understanding (SLU), and machine learning methods for system optimisation, either during online operation, simulation, or from small amounts of data. %@ 978-1-4614-4802-0

@book{LemonPietquin2012, abstract = {The EC FP7 project 'Computational Learning in Adaptive Systems for Spoken Conversation' (CLASSiC) was a European initiative working on a fully data-driven architecture for the development of conversational interfaces, as well as new machine learning approaches for their sub-components. It developed a variety of novel statistical methods for spoken dialogue processing, for extended conversational interaction, which are now collected together in this book. A major focus of the project was in tracking the accumulation of information about user goals over multiple dialogue turns (i.e. extended conversational interaction), and in maintaining overall system robustness even when speech recognition results contain errors, by managing uncertainty through the processing chain. Other advances were made in the areas of adaptive natural language generation (NLG), statistical methods for spoken language understanding (SLU), and machine learning methods for system optimisation, either during online operation, simulation, or from small amounts of data.}, added-at = {2017-10-31T16:39:05.000+0100}, address = {New York}, biburl = {https://www.bibsonomy.org/bibtex/2744018c7067f48f05cfd69e9ac2bb43b/flint63}, doi = {10.1007/978-1-4614-4803-7}, editor = {Lemon, Oliver and Pietquin, Olivier}, file = {SpringerLink:2012/LemonPietquin2012.pdf:PDF;Springer Product page:http\://www.springer.com/978-1-4614-4802-0:URL;SpringerPro:https\://www.springerprofessional.de/data-driven-methods-for-adaptive-spoken-dialogue-systems/1854750:URL;Amazon Search inside:http\://www.amazon.de/gp/reader/1461448026/:URL}, groups = {public}, interhash = {b873431485fd449c75eaebc2134e9db9}, intrahash = {744018c7067f48f05cfd69e9ac2bb43b}, isbn = {978-1-4614-4802-0}, keywords = {01801 103 springer book numerical ai adaptive language processing analysis generation dialog user interface interaction learn zzz.sds}, publisher = {Springer}, timestamp = {2018-04-16T11:38:50.000+0200}, title = {Data-Driven Methods for Adaptive Spoken Dialogue Systems: Computational Learning for Conversational Interfaces}, username = {flint63}, year = 2012 }