Trace &amp; Unification Grammar

Block, Hans Ulrich; Schachtl, Stefanie

doi:10.3115/992066.992083

Cited by 12 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[3], [4]. In the module described here, a Trace and Unification Grammar (TUG) [12] and a modification of the parsing algorithm of Tomita [50] is used. The basis of a TUG is a context free grammar augmented with PATR-II-style feature equations.…”

Section: A Prosody and Syntax-interaction With The Tug-grammarmentioning

confidence: 99%

VERBMOBIL: the use of prosody in the linguistic components of a speech understanding system

Nöth

Batliner

Kießling

et al. 2000

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

In this paper, we show how prosody can be used in speech understanding systems. This is demonstrated with the VERBMOBIL speech-to-speech translation system which, to our knowledge, is the first complete system which successfully uses prosodic information in the linguistic analysis. Prosody is used by computing probabilities for clause boundaries, accentuation, and different types of sentence mood for each of the word hypotheses computed by the word recognizer. These probabilities guide the search of the linguistic analysis. Disambiguation is already achieved during the analysis and not by a prosodic verification of different linguistic hypotheses. So far, the most useful prosodic information is provided by clause boundaries. These are detected with a recognition rate of 94%. For the parsing of word hypotheses graphs, the use of clause boundary probabilities yields a speed-up of 92% and a 96% reduction of alternative readings.

show abstract

Section: A Prosody and Syntax-interaction With The Tug-grammarmentioning

confidence: 99%

VERBMOBIL: the use of prosody in the linguistic components of a speech understanding system

Nöth

Batliner

Kießling

et al. 2000

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

show abstract

“…[1,2]. In the module described here, we use a Trace and Unification Grammar (TUG) [7] and a modification of the parsing algorithm of Tomita [33]. The basis of a TUG is a context free grammar augmented with PATR-II-style feature equations.…”

Section: Prosody and Syntax -Interaction With The Tug-grammarmentioning

confidence: 99%

Suprasegmental Modelling

Nöth

Batliner

Kießling

et al. 1999

Computational Models of Speech Pattern Processing

View full text Add to dashboard Cite

We show how prosody can be used in speech understanding systems. This is demonstrated with the VERBMOBIL speech-to-speech translation system, the world wide first complete system, which successfully uses prosodic information in the linguistic analysis. Prosody is used by computing probabilities for clause boundaries, accentuation, and different types of sentence mood for each of the word hypotheses computed by the word recognizer. These probabilities guide the search of the linguistic analysis. Disambiguation is already achieved during the analysis and not by a prosodic verification of different linguistic hypotheses. So far, the most useful prosodic information is provided by clause boundaries. These are detected with a recognition rate of 94%. For the parsing of word hypotheses graphs, the use of clause boundary probabilities yields a speed-up of 92% and a 96% reduction of alternative readings.

show abstract

“…We use a Trace and Unification Grammar (TUG) [3] and a modification of the parsing algorithm of Tomita [9]. The basis of a TUG is a context free grammar augmented with PATR-II-style feature equations.…”

Section: Grammar and Parsermentioning

confidence: 99%

Improving parsing by incorporating 'prosodic clause boundaries into a grammar

Bakenecker¹,

Block²,

Batliner³

et al. 1994

3rd International Conference on Spoken Language Processing (ICSLP 1994)

View full text Add to dashboard Cite

In written language, punctuation is used to separate main and subordinate clause. In spoken language, ambiguities arise due to missing punctuation, but clause boundaries are often marked prosodically and can be used instead. We detect PCBs (Prosodically marked Clause Boundaries) by using prosodic features (duration, intonation, energy, and pause information) with a neural network, achieving a recognition rate of 82%. PCBs are integrated into our grammar using a special syntactic category 'break' that can be used in the phrase-structure rules of the grammar in a similar way as punctuation is used in grammars for written language. Whereas punctuation in most cases is obligatory, PCBs are sometimes optional. Moreover, they can in principle occur everywhere in the sentence due e.g. to hesitations or misrecognition. To cope with these problems we tested two different approaches: A slightly modified parser for word chains containing PCBs and a word graph parser that takes the probabilities of PCBs into account. Tests were conducted on a subset of infinitive subordinate clauses from a large speech database containing sentences from the domain of train table inquiries. The average number of syntactic derivations could be reduced by about 70 % even when working on recognized word graphs.

show abstract

Trace & Unification Grammar

Cited by 12 publications

References 7 publications

VERBMOBIL: the use of prosody in the linguistic components of a speech understanding system

VERBMOBIL: the use of prosody in the linguistic components of a speech understanding system

Suprasegmental Modelling

Improving parsing by incorporating 'prosodic clause boundaries into a grammar

Contact Info

Product

Resources

About