A Persian G2P system using an LLM-generated "Pinglish" intermediate representation and a seq2seq model reports PER 0.0196 and BLEU 94.6, but the supporting tables are missing and the evaluation is largely self-referential.
From the initial 64,000 entries, we allocated 1,000 samples each for validation and test evaluation, with the remaining 62,000 samples designated for training data augmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Bridging the Gap: An Intermediate Language for Enhanced and Cost-Effective Grapheme-to-Phoneme Conversion with Homographs with Multiple Pronunciations Disambiguation
A Persian G2P system using an LLM-generated "Pinglish" intermediate representation and a seq2seq model reports PER 0.0196 and BLEU 94.6, but the supporting tables are missing and the evaluation is largely self-referential.