Metraipolis › archive › dc_c4eec0618211

Low-Latency Spell Correction for Japanese Music Search Queries — arXiv:2609.04262

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04262
License (as archived): CC0-1.0
Archived: 2026-10-16T22:59:51.041Z
SHA-256 of the archived text: 076629749a067742021c9badac5f5a0744a2bcc66e8406fe8be02e27e27ef141
Stable URL of this page: https://metraipolis.com/documento/dc_c4eec0618211

How to cite

Low-Latency Spell Correction for Japanese Music Search Queries — arXiv:2609.04262 — arXiv (en), https://arxiv.org/abs/2609.04262 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4eec0618211 (Metraipolis archive dc_c4eec0618211, sha256 076629749a067742021c9badac5f5a0744a2bcc66e8406fe8be02e27e27ef141)

BibTeX

@misc{dcc4eec0618211,
  title = {Low-Latency Spell Correction for Japanese Music Search Queries — arXiv:2609.04262},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04262},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4eec0618211; sha256 076629749a067742021c9badac5f5a0744a2bcc66e8406fe8be02e27e27ef141},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04262. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spell correction for Japanese search queries presents unique challenges due to the co-existence of four writing scripts (Latin/romaji, hiragana, katakana, and kanji) and the distinct error patterns each script induces. We present a compact BART-based sequence-to-sequence model (3 encoder + 3 decoder layers) designed for low-latency spell correction of Japanese music search queries. The core contribution lies in a script-aware synthetic misspelling generation pipeline that produces realistic training data by combining keyboard-layout models (QWERTY and flick input), phonetic confusion priors mined from real query logs, voiced/unvoiced consonant alternations, and kana case errors. A key design decision is normalizing mixed-script catalog titles to a single canonical script before misspelling synthesis, which we show is critical for reducing model hallucinations. We train a custom byte-level BPE tokenizer on the target music catalog to handle all four scripts in a unified vocabulary. Experiments on a curated evaluation set show that our model achieves an exact-match accuracy of 41.09% and a character error rate (CER) of 11.62%, outperforming edit-distance baselines and achieving the lowest character error rate among all evaluated systems while maintaining sub-4ms inference latency on a single GPU. We further analyze performance across individual scripts and mixed-script queries, demonstrating the effectiveness of script-aware data augmentation through systematic ablation studies.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.LG).
Categorie arXiv: Sound (cs.SD) ; Machine Learning (cs.LG); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.04262 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T22:31:32.225Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).