% % GENERATED FROM https://www.coli.uni-saarland.de % by : anonymous % IP : coli2006.lst.uni-saarland.de % at : Mon, 05 Feb 2024 15:43:28 +0100 GMT % % Selection : Author: Hans_Weber % @TechReport{Kasper_et_al:1996, AUTHOR = {Kasper, Walter and Krieger, Hans-Ulrich and Spilker, Jörg and Weber, Hans}, TITLE = {From Word Hypotheses to Logical Form: An Efficient Interleaved Approach}, YEAR = {1996}, NUMBER = {142}, ADDRESS = {Saarbrücken}, TYPE = {Verbmobil-Report}, INSTITUTION = {DFKI}, URL = {ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/konvens96.ps.gz}, ABSTRACT = {This paper revisits word lattice parsing whose task is to find a plausible semantic interpretation for a given utterance. Our approach of interleaved search and analysis is designed to break the frontier of toy applications. The framework is implemented in two interacting modules, running in parallel. Instead of simply parsing a word lattice, we rather do tree decoding with a probabilistic approximation of a given grammar, employing a beam search strategy. Logical form is build up in tandem according to the decoded derivation histories, using a codescriptive HPSG grammar for dialog turns. In diesem Papier betrachten wir auf neue Weise Wortgraphenparsing, dessen Aufgabe es ist, eine plausible semantische Interpretation fuer eine gegebene Aufforderung zu finden. Unser Ansatz von ueberlagerter Suche und Analyse ist mit dem Ziel entwickelt worden, die Grenzen von Spielapplikationen zu durchbrechen. Das System ist in zwei interagierenden, parallel arbeitenden Modulen implementiert. Anstatt einen Wortgraphen direkt zu parsen, dekodieren wir Baeume mit einer probabilistischen Approximation einer gegebene Grammatik unter Verwendung einer Strahlensuche. Logische Form wird gemaess den Ableitungshistorien gleichzeitig mit aufgebaut, wobei eine HPSG Grammatik fuer Dialoge eingesetzt wird.}, ANNOTE = {COLIURL : Kasper:1996:WHLb.pdf Kasper:1996:WHLb.ps} } @InProceedings{Kasper_et_al:1996_1, AUTHOR = {Kasper, Walter and Krieger, Hans-Ulrich and Spilker, Jörg and Weber, Hans}, TITLE = {From Word Hypotheses to Logical Form: An Efficient Interleaved Approach}, YEAR = {1996}, BOOKTITLE = {Proceedings of the Natural Language Processing and Speech Technology: Results of the 3rd KONVENS Conference, October 7-9}, PAGES = {77-88}, EDITOR = {Gibbon, Dafydd}, ADDRESS = {Bielefeld, Germany}, PUBLISHER = {Mouton de Gruyter}, URL = {ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/konvens96.ps.gz ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/konvens96.entry}, ABSTRACT = {This paper revisits word lattice parsing whose task is to find a plausible semantic interpretation for a given utterance. Our approach of interleaved search and analysis is designed to break the frontier of toy applications. The framework is implemented in two interacting modules, running in parallel. Instead of simply parsing a word lattice, we rather do tree decoding with a probabilistic approximation of a given grammar, employing a beam search strategy. Logical form is build up in tandem according to the decoded derivation histories, using a codescriptive HPSG grammar for dialog turns. In diesem Papier betrachten wir auf neue Weise Wortgraphenparsing, dessen Aufgabe es ist, eine plausible semantische Interpretation fuer eine gegebene Aufforderung zu finden. Unser Ansatz von ueberlagerter Suche und Analyse ist mit dem Ziel entwickelt worden, die Grenzen von Spielapplikationen zu durchbrechen. Das System ist in zwei interagierenden, parallel arbeitenden Modulen implementiert. Anstatt einen Wortgraphen direkt zu parsen, dekodieren wir Baeume mit einer probabilistischen Approximation einer gegebene Grammatik unter Verwendung einer Strahlensuche. Logische Form wird gemaess den Ableitungshistorien gleichzeitig mit aufgebaut, wobei eine HPSG Grammatik fuer Dialoge eingesetzt wird.}, ANNOTE = {COLIURL : Kasper:1996:WHLa.pdf Kasper:1996:WHLa.ps} } @InProceedings{Ruland_et_al:1998, AUTHOR = {Ruland, Tobias and Rupp, Christopher J. and Spilker, Jörg and Weber, Hans and Worm, Karsten L.}, TITLE = {Making the Most of Multiplicity: A Multi-Parser Multi-Strategy Architecture for the Robust Processing of Spoken Language}, YEAR = {1998}, BOOKTITLE = {Prceedings of the 5th International Conference on Spoken Language Processing (ICSLP'98), November 30 - December 4}, EDITOR = {Mannell, Robert H. and Robert-Ribes, Jordi}, ADDRESS = {Sydney, Australia}, PUBLISHER = {ASSTA} } @InProceedings{Strom_et_al:1997, AUTHOR = {Strom, Volker and Elsner, Aanja and Hess, Wolfgang and Kasper, Walter and Klein, Alexandra and Krieger, Hans-Ulrich and Spilker, Jörg and Weber, Hans and Görz, Günther}, TITLE = {On the Use of Prosody in a Speech-to-Speech Translator}, YEAR = {1997}, BOOKTITLE = {Proceedings of the 5th Biennial European Conference on Speech Communication and Technology (Eurospeech'97), September 22-25}, PAGES = {1479-1482}, ADDRESS = {Rhodes, Greece}, URL = {ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/eurospeech_paper.ps.gz ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/eurospeech97.entry}, ABSTRACT = {In this paper a speech-to-speech translator from German to English is presented. Beside the traditional processing steps it takes advantage of acoustically detected prosodic phrase boundaries and focus. The prosodic phrase boundaries reduce search space during syntactic parsing and rule out analysis trees during semantic parsing. The prosodic focus faciliates a shallow translation based on the best word chain in cases where the deep analysis fails.}, ANNOTE = {COLIURL : Strom:1997:UPS.ps} }