Recovering From Parser Failures: A Hybrid Statistical/Symbolic Approach

Simple item page
dc.creatorRose', Carolyn Penstein
dc.creatorWaibel, Alex
dc.date1994-07-28
dc.date.accessioned2026-07-07T09:09:26Z
dc.date.available2026-07-07T09:09:26Z
dc.descriptionWe describe an implementation of a hybrid statistical/symbolic approach to repairing parser failures in a speech-to-speech translation system. We describe a module which takes as input a fragmented parse and returns a repaired meaning representation. It negotiates with the speaker about what the complete meaning of the utterance is by generating hypotheses about how to fit the fragments of the partial parse together into a coherent meaning representation. By drawing upon both statistical and symbolic information, it constrains its repair hypotheses to those which are both likely and meaningful. Because it updates its statistical model during use, it improves its performance over time.
dc.identifierhttps://arxiv.org/abs/cmp-lg/9407025
dc.identifierhttp://arxiv.org/abs/cmp-lg/9407025
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151036
dc.subjectComputation and Language
dc.titleRecovering From Parser Failures: A Hybrid Statistical/Symbolic Approach
dc.typetext

Files

Collections

arXiv