Deep Processing Shallow Processing Generation German Synthesis
نویسنده
چکیده
verbmobil, a speech to speech translation system, poses new and challenging tasks for a dialogue component. We present a part of the dialogue component of verbmobil: a robust plan recognizer that processes all of the over 200 dialogues of the verb-mobil corpus. The recognizer currently handles unexpected sequences of input, and will in the future deal with multiple input, hypotheses, and incomplete input.
منابع مشابه
Shallow ProcessingDeep Processing Synthesis SynthesisTransfer Prosodic - Generation Recording Dialogue Processing EnglishEnglish Generation German German
In this paper we show how the notion of context has been reened in order to fullll the requirements posed by a natural language processing system. We describe the context model of the speech translation system verbmobil which has been derived from constraints given by various subcomponents of the system. In verbmo-bil context is stored in the dialogue memory which is incrementally constructed b...
متن کاملFlexible Shortcuts: Linguistic Distributional Information Affects both Shallow and Deep Conceptual Processing
Previous research has shown that people use both embodied perceptual simulations and linguistic distributional knowledge during conceptual processing, with linguistic information especially useful for shallow tasks and rapid responding. Using two conceptual combination tasks, we show that this linguistic shortcut is evident in both shallow and deep conceptual processing of novel stimuli. Specif...
متن کاملBalanced bilinguals favor lexical processing in their opaque language and conversion system in their shallow language.
Referred to as orthographic depth, the degree of consistency of grapheme/phoneme correspondences varies across languages from high in shallow orthographies to low in deep orthographies. The present study investigates the impact of orthographic depth on reading route by analyzing evoked potentials to words in a deep (French) and shallow (German) language presented to highly proficient bilinguals...
متن کاملFlexible and fast: linguistic shortcut affects both shallow and deep conceptual processing.
Previous research has shown that people use linguistic distributional information during conceptual processing, and that it is especially useful for shallow tasks and rapid responding. Using two conceptual combination tasks, we showed that this linguistic shortcut extends to the processing of novel stimuli, is used in both successful and unsuccessful conceptual processing, and is evident in bot...
متن کاملWhich Semantics for Requirements Engineering: From Shallow to Deep
Natural language processing has been proposed and applied to support a variety of tasks in requirements engineering. While shallow semantic allows to address many of the challenges, to further automatize requirements analysis a full understanding of textual requirements is needed. To this end, the future generation of natural language processing systems needs a deep semantics, that is a represe...
متن کامل