arXiv cs.CL· Ahmet Tu\u{g}rul Bayrak, Fatma Nur Korkmaz, Nur Ya\u{g}mur Tuncer, Mustafa Serta\c{c} T\"urkel·· 11 小时前AI 评分22
TurnTurk-GPT：面向土耳其语的基于文本的轮次转换预测
TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish
AI 导读
TurnTurk-GPT 通过用 TurnGPT 目标微调土耳其语 GPT-2 模型，构建了土耳其语文本轮次转换预测器，在 recording-disjoint 和 speaker-disjoint 评估下均优于现有多语言轮次结束检测器。
正文 · 原文
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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.42010 [cs.CL] |
| (or arXiv:2610.42010v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.42010 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ahmet Tuğrul Bayrak [view email]
[v1]
Fri, 30 Oct 2026 16:48:32 UTC (80 KB)
来源：arXiv cs.CL · arxiv.org