Acquiring lexical information from multilevel temporal annotations
The extraction of lexical information for machine readable lexica from multilevel annotations is addressed in this paper. Relations between these levels of annotation are used for subclassification of lexical entries. A method for relating annotation...
mehr
|
Volltext:
|
|
|
Zitierfähiger Link:
|
|
|
The extraction of lexical information for machine readable lexica from multilevel annotations is addressed in this paper. Relations between these levels of annotation are used for subclassification of lexical entries. A method for relating annotation units is presented, based on a temporal calculus. Relating the annotation units manually is errorprone, time consuming and tends to be inconsistent, and a method is presented for automatically accomplishing this task, and evaluated using German, Japanese and Anyi (W. Africa) corpora.
|
| Export in Literaturverwaltung |
|
A computational model of arm gestures in conversation
Currently no standardised gesture annotation systems are available. As a contribution towards solving this problem, CoGesT, a machine processable and human usable computational model for the annotation of a subset of conversational gestures is...
mehr
|
Volltext:
|
|
|
Zitierfähiger Link:
|
|
|
Currently no standardised gesture annotation systems are available. As a contribution towards solving this problem, CoGesT, a machine processable and human usable computational model for the annotation of a subset of conversational gestures is presented, its empirical and formal properties are detailed, and application areas are discussed.
|
| Export in Literaturverwaltung |
|
Concordancing for parallel spoken language corpora
Concordancing is one of the oldest corpus analysis tools, especially for written corpora. In NLP concordancing appears intraining of speech-recognition system. Additionally, comparative studies of different languages result in parallel corpora....
mehr
|
Volltext:
|
|
|
Zitierfähiger Link:
|
|
|
Concordancing is one of the oldest corpus analysis tools, especially for written corpora. In NLP concordancing appears intraining of speech-recognition system. Additionally, comparative studies of different languages result in parallel corpora. Concordancing for these corpora in a NLP context is a new approach. We propose to combine these fields of interest for a multi-purpose concordance for Spoken Language Data, opening the opportunity of combining corpus-linguistic and NLP methods resulting in a broader empirical basis for NLP research. Theoretic models for audio-concordances are discussed. Principles of the structure and design of a parallel audio concordance are given, coding by means of XML to ensure reusability and flexibility, using time stamps for referencing from annotations to the signal.
|
| Export in Literaturverwaltung |
|
Terminology principles and support for spoken language system development
Spoken language (SL) system development is an increasingly interdisciplinary effort. Speech-to-speech system development, for example, involves speech engineers, software engineers, phoneticians, and a variety of computational linguistic...
mehr
|
Volltext:
|
|
|
Zitierfähiger Link:
|
|
|
Spoken language (SL) system development is an increasingly interdisciplinary effort. Speech-to-speech system development, for example, involves speech engineers, software engineers, phoneticians, and a variety of computational linguistic subdisciplines from morphology, syntax and lexicology through semantics and pragmatics, each with their own historically motivated terminology. In our experience this ‘terminology barrier’ makes communication between the disciplines unnecessarily difficult. As a contribution to reducing the terminology barrier we propose a set of new speech specific terminological principles and a prototype term bank with an Internet interface for this specific purpose. The result is one of the outputs of the spoken language working group of the LE EAGLES Phase II project (LE3-4244 10484/0).
|
| Export in Literaturverwaltung |
|
