Modularity in Inductively-Learned Word Pronunciation Systems
Explore this paper's citation graph
Summary
This work trains and test three word-pronunciation systems in which the number of abstraction levels (implemented as sequenced modules) is reduced from five, via three, to one, andalyses of empirical results indicate that positive utility effects of sequencing modules are outweighed by cascading errors passed on between modules.
- Type
- article
- Published
- 1998-01-11
- Cited by
- 14
- References
- 36
- Access
- Open access
- OpenAlex
- https://openalex.org/W1978513506
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:7480074
Keywords
Pronunciation, Computer science, Word (group theory), Natural language processing, Artificial intelligence
References
- Prononcer par analogie : motivation, formalisation et evaluation
- Programs for Machine Learning
- Computer Systems That Learn
- The Acquisition of Stress: A Data-Oriented Approach
- The Sound Pattern of English
- The Theory of Lexical Phonology
- Toward memory-based reasoning
- Data-Oriented Methods for Grapheme-to-Phoneme Conversion
- Constructing a generalizer superior to NETtalk via a mathematical theory of generalization
- Language and Learning: The Debate Between Jean Piaget and Noam Chomsky
- A General Computational Model for Word-Form Recognition and Production
- GRAFON: A Grapheme-to-Phoneme Conversion System for Dutch
- C4.5: Programs for Machine Learning
- Language and Learning: The Debate between Jean Piaget and Noam Chomsky
- Neurological Aspects of Human Retroviruses (Baillière's Clinical Neurology
- Generalization performance of backpropagation learning on a syllabification task
- Experience-driven language acquisition and processing
- Language-Independent Data-Oriented Grapheme-to-Phoneme Conversion
- Classification and Regression Trees
- Phonological Rules for a Text-to-Speech System
Cited by
- Improving Pronunciation Accuracy of Proper Names with Language Origin Classes
- Letter-to-sound for small-footprint multilingual TTS engine
- A machine learning approach to Swedish word pronunciation
- Letter to sound rules for accented lexicon compression
- Issues in building general letter to sound rules
- Phonological Constraints and Morphological Preprocessing for Grapheme-to-Phoneme Conversion
- Part-of-speech Tagging: A Machine Learning Approach based on Decision Trees
- Beyond the Pipeline: Discrete Optimization in NLP
- RECEPTORS AND SYLLABLE TRAJECTORIES
- Letter-to-Phoneme Conversion for a German Text-to-Speech System
- Representational Bias in Unsupervised Learning of Syllable Structure
- Modeling Linguistic Phenomena in Gallo-Italic Dialects: The Linguistic Phenomena Ontology
- TO SOUND RULES FOR ACCENTED LEXICON COMPRESSION
- Machine Learning and Natural Language Processing
Related papers
- The Phonetics and Phonology of some Syllabic Consonants in Southern British English
- Effect of syllabic neighbourhood as a function of syllabic neighbour length
- The Syllabic Features of the Chinese New Words
- Syllabic structure and the acquisition of consonants: The great conspiracy in word formation
- Syllabic Consonants in Historical Czech and How to Identify Them
- Syllabic consonants in Polish
- Формы интерпретации тюркского силлабического стиха в русской поэзии
- Phonology and spelling: the case of syllabic consonants.
- On Variant Chinese Character and Homepone of Syllabic Language in Jiangyong Female Shared Literature
- Моносиллабизм и фонологическая релевантность слога