Learning to pronounce as measuring cross-lingual joint orthography-phonology complexity
원문 초록
Machine learning models allow us to compare languages by showing how hard a task in each language might be to learn and perform well on. Following this line of investigation, we explore what makes a language "hard to pronounce" by modelling the task of grapheme-to-phoneme (g2p) transliteration. By training a character-level transformer model on this task across 22 languages and measuring the model's proficiency against its grapheme and phoneme inventories, we show that certain characteristics emerge that separate easier and harder languages with respect to learning to pronounce. Namely the complexity of a language's pronunciation from its orthography is due to the expressive or simplicity of its grapheme-to-phoneme mapping. Further discussion illustrates how future studies should consider relative data sparsity per language to design fairer cross-lingual comparison tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ParsiPy: NLP Toolkit for Historical Persian Texts in Python
Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches
Romanized to Native Malayalam Script Transliteration Using an Encoder-Decoder Framework
GR-NLP-TOOLKIT: An Open-Source NLP Toolkit for Modern Greek
How Transliterations Improve Crosslingual Alignment
Can Small Language Models Learn, Unlearn, and Retain Noise Patterns?
토론
이 논문과 연결된 포럼 글이 아직 없습니다.