| title | TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish |
|---|---|
| authors | Ahmet Tuğrul Bayrak, Fatma Nur Korkmaz, Nur Yağmur Tuncer, Mustafa Sertaç Türkel |
| date | 2026-10-30 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.42010 |
| upvotes | 1 (Hugging Face Daily Papers, 2026-11-03) |
| links | abs pdf hf |
| abstract | 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. |
cite
@misc{bayrak2026turnturk,
title={TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish},
author={Ahmet Tuğrul Bayrak and Fatma Nur Korkmaz and Nur Yağmur Tuncer and Mustafa Sertaç Türkel},
year={2026},
eprint={2610.42010},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.42010}
}