论文信息 - Pronouncing unknown words using multi-dimensional analogies

Pronouncing unknown words using multi-dimensional analogies

In this paper, a model of analogy-based learning is presented, whose main novelty is the crucial ability to produce analogies in multi-dimensional input and output spaces. Evaluations are performed on various word pronunciation tasks, revealing the effectiveness of such joint learning strategies.

François Yvon

[1] Howard C. Nusbaum,et al. Pronounce : a program for pronunciation by analogy , 1991 .

[2] Vito Pirrelli,et al. The hidden dimension: a paradigmatic view of data-driven NLP , 1999, J. Exp. Theor. Artif. Intell..

[3] Gavin Burnage. Celex-a guide for users , 1990 .

[4] François Yvon. Grapheme-to-Phoneme Conversion using Multiple Unbounded Overlapping Chunks , 1996, ArXiv.

[5] A.P.J. van den Bosch,et al. Learning to pronounce written words : a study in inductive language learning , 1997 .

[6] Robert I. Damper,et al. Improving pronunciation by analogy for text-to-speech applications , 1998, SSW.

[7] Ellen Riloff,et al. Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing , 1996, Lecture Notes in Computer Science.

[8] Tony Vitale,et al. An Algorithm for High Accuracy Name Pronunciation by Parametric Speech Synthesizer , 1991, Comput. Linguistics.

[9] Robert I. Damper,et al. Novel-word pronunciation within a text-to-speech system , 1990, SSW.

[10] Terrence J. Sejnowski,et al. Parallel Networks that Learn to Pronounce English Text , 1987, Complex Syst..

[11] Vito Pirrelli,et al. A dynamic approach to paradigm-driven analogy , 1995, Learning for Natural Language Processing.