---
title: "TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.42010v1"
permalink: "https://feed.astralor.com/items/itm_f4182da32e467d3e50badec1"
published: "2026-10-30T16:48:32.000Z"
score: 54
channel: "ai"
tags: ["OpenAI","TurnTurk-GPT","Text-Based Turn-Taking Prediction","Turkish This","Turkish","Turkish GPT-2","TurnGPT"]
---

# TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish

## At a glance

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 …

## Key points

- 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 …
- 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…
- TurnTurk-GPT outperforms the multilingual detector under both recording-disjoint and speaker-disjoint evaluation.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_f4182da32e467d3e50badec1