Metraipolis › archive › dc_4624ce035fbe

TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish — arXiv:2610.42010

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.42010
License (as archived)
CC0-1.0
Archived
2026-11-02T04:46:20.621Z
SHA-256 of the archived text
de0519d8051048c8f989b2a9d5b3f5ecaafb471c9a2939f537a6f17a0be77393
Stable URL of this page
https://metraipolis.com/documento/dc_4624ce035fbe

How to cite

TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish — arXiv:2610.42010 — arXiv (en), https://arxiv.org/abs/2610.42010 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4624ce035fbe (Metraipolis archive dc_4624ce035fbe, sha256 de0519d8051048c8f989b2a9d5b3f5ecaafb471c9a2939f537a6f17a0be77393)
BibTeX
@misc{dc4624ce035fbe,
  title = {TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish — arXiv:2610.42010},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42010},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4624ce035fbe; sha256 de0519d8051048c8f989b2a9d5b3f5ecaafb471c9a2939f537a6f17a0be77393},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42010. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper presents TurnTurk-GPT, a text-based turn-taking predictor for Turkish obtained by fine-tuning a Turkish GPT-2 model with the TurnGPT objective on synthetic and real dialogue, and evaluates it on real Turkish conversation against rule baselines, a zero-shot Turkish language model and a widely used multilingual end-of-turn detector. Evaluation uses word-level decision points on unpunctuated, lower-cased text approximating the output of streaming speech recognisers, recording-disjoint and speaker-disjoint folds, nested threshold selection and paired cluster bootstrap tests. TurnTurk-GPT outperforms the multilingual detector under both recording-disjoint and speaker-disjoint evaluation. It outperforms the zero-shot language model only when the test speakers occur in training; on unseen speakers the two are statistically indistinguishable. Removing the suffixes of the turn-final word reduces AP by up to 44%, against 2% for a sentence-internal word, locating the Turkish end-of-turn cue in verb-final morphology. Synthetic dialogue alone yields the weakest trained model, and when a speaker pauses the zero-shot and multilingual baselines remain close to chance. The model and the evaluation protocol are publicly released.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.42010 — 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 2026-11-02T04:42:26.915Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).