ABSTRACT
The speed with which pronunciation dictionaries can be bootstrapped depends on the efficiency of learning algorithms and on the ordering of words presented to the user. This paper presents an active-learning word selection strategy that is mindful of human limitations. Learning rates approach that of an oracle system that knows the final LTS rule set.
- Peter Auer, 2000. Using upper confidence bounds for online learning. Proceedings of the 41st Annual Symposium on Foundations of Computer Science, pp. Google ScholarDigital Library
- Alan W Black, Kevin Lenzo, and Vincent Pagel, 1998. Issues in Building General Letter to Sound Rules. 3rd ESCA Workshop on Speech Synthesis, Australia.Google Scholar
- Gavin Burnage, 1990. CELEX - A Guide for Users. Hijmegen: Centre for Lexical Information, University of Nijmegen.Google Scholar
- Piero Cosi, Roberto Gretter, Fabio Tesser, 2000. Festival parla italiano. Proceedings of GFS2000, Giornate del Gruppo di Fonetica Sperimentale, Padova.Google Scholar
- Marelie Davel and Etienne Barnard, 2003. Bootstrapping in Language Resource Generation. Proceedings of the 14th Symposium of the Pattern Recognition Association of South Africa, pp. 97--100.Google Scholar
- Marelie Davel and Etienne Barnard, 2004. A default-and-refine approach to pronunciation prediction, Proceedings of the 15th Symposium of the Pattern Recognition Association of South Africa.Google Scholar
- Marelie Davel and Etienne Barnard, 2005. Bootstrapping Pronunciation Dictionaries: Practical Issues. Proceedings of the 9th International Conference on Spoken Language Processing, Lisbon, Portugal.Google Scholar
- Herman Engelbrecht, Tanja Schultz, 2005. Rapid Development of an Afrikaans-English Speech-to-Speech Translator, International Workshop on Spoken Language Translation, Pittsburgh, PA. pp. 169--176.Google Scholar
- S P Kishore and Alan W Black, 2003. Unit Size in Unit Selection Speech Synthesis. Proceedings of the 8th European Conference on Spoken Language Processing, Geneva, Switzerland.Google Scholar
- Alon Lavie, et al. 2003. Experiments with a Hindi-to-English Transfer-based MT System under a Miserly Data Scenario, ACM Transactions on Asian Language Information Processing, 2(2). Google ScholarDigital Library
- Piet Mertens and Filip Vercammen, 1998. Fonilex Manual, Technical Report, K. U. Leuven CCL.Google Scholar
- John Wells and Jill House, 1995. Sounds of the IPA. http://www.phon.ucl.ac.uk/shop/soundsipa.php.Google Scholar
- Learning pronunciation dictionaries: language complexity and word selection strategies
Recommendations
Bootstrapping dictionaries for cross-language information retrieval
SIGIR '05: Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrievalThe bottleneck for dictionary-based cross-language information retrieval is the lack of comprehensive dictionaries, in particular for many different languages. We here introduce a methodology by which multilingual dictionaries (for Spanish and Swedish) ...
Creating sentiment dictionaries via triangulation
The paper presents a semi-automatic approach to creating sentiment dictionaries in many languages. We first produced high-level gold-standard sentiment dictionaries for two languages and then translated them automatically into third languages. Those ...
Comments