Academic Journals Database
Disseminating quality controlled scientific knowledge

Prédiction des frontières prosodiques de syntagmes: problèmes dans l'évaluation de modèles par rapport à une référence Prosodic Phrase Break Prediction: Problems in the Evaluation of Models against a Gold Standard

Author(s): Claire Brierley | Eric Atwell

Journal: Traitement Automatique des Langues
ISSN 1248-9433

Volume: 48;
Issue: 1;
Start page: 187;
Date: 2008;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: evaluation | prosody | supervised learning | statistical methods

The goal of automatic phrase break prediction is to identify prosodic-syntactic boundaries in text which correspond to the way a native speaker might process or chunk that same text as speech. This is treated as a classification task in machine learning and output predictions from language models are evaluated against a ‘gold standard': human-labelled prosodic phrase break annotations in transcriptions of recorded speech - the speech corpus. Despite the introduction of rigorous metrics such as precision and recall, the evaluation of phrase break models is still problematic because prosody is inherently variable; morphosyntactic analysis and prosodic annotations for a given text are not representative of the range of parsing and phrasing strategies available to, and exhibited by, native speakers. This article recommends creating automatically-generated POS tagged and prosodically annotated variants of a text to enrich the gold standard and enable more robust ‘noise-tolerant' evaluation of language models.

Tango Rapperswil
Tango Rapperswil

     Save time & money - Smart Internet Solutions