PolyIPA -- Multilingual Phoneme-to-Grapheme Conversion Model
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916519877804032 |
|---|---|
| author | Lauc, Davor |
| author_facet | Lauc, Davor |
| contents | This paper presents PolyIPA, a novel multilingual phoneme-to-grapheme conversion model designed for multilingual name transliteration, onomastic research, and information retrieval. The model leverages two helper models developed for data augmentation: IPA2vec for finding soundalikes across languages, and similarIPA for handling phonetic notation variations. Evaluated on a test set that spans multiple languages and writing systems, the model achieves a mean Character Error Rate of 0.055 and a character-level BLEU score of 0.914, with particularly strong performance on languages with shallow orthographies. The implementation of beam search further improves practical utility, with top-3 candidates reducing the effective error rate by 52.7\% (to CER: 0.026), demonstrating the model's effectiveness for cross-linguistic applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09102 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PolyIPA -- Multilingual Phoneme-to-Grapheme Conversion Model Lauc, Davor Computation and Language Artificial Intelligence This paper presents PolyIPA, a novel multilingual phoneme-to-grapheme conversion model designed for multilingual name transliteration, onomastic research, and information retrieval. The model leverages two helper models developed for data augmentation: IPA2vec for finding soundalikes across languages, and similarIPA for handling phonetic notation variations. Evaluated on a test set that spans multiple languages and writing systems, the model achieves a mean Character Error Rate of 0.055 and a character-level BLEU score of 0.914, with particularly strong performance on languages with shallow orthographies. The implementation of beam search further improves practical utility, with top-3 candidates reducing the effective error rate by 52.7\% (to CER: 0.026), demonstrating the model's effectiveness for cross-linguistic applications. |
| title | PolyIPA -- Multilingual Phoneme-to-Grapheme Conversion Model |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2412.09102 |