@inproceedings{egin-onan-2026-tr,
title = "{TR}-{E}du{VS}um: A {T}urkish-Focused Dataset and Consensus Framework for Educational Video Summarization",
author = "E{\u{g}}in, Figen and
Onan, Aytu{\u{g}}",
editor = {Oflazer, Kemal and
K{\"o}ksal, Abdullatif and
Varol, Onur},
booktitle = "Proceedings of the Second Workshop Natural Language Processing for {T}urkic Languages ({SIGTURK} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigturk-1.5/",
pages = "52--60",
ISBN = "979-8-89176-370-8",
abstract = "This study presents a framework for generating the gold-standard summary fully automatically and reproducibly based on multiple human summaries of Turkish educational videos. Within the scope of the study, a new dataset called TR-EduVSum was created, encompassing 82 Turkish course videos in the field of ``Data Structures and Algorithms'' and containing a total of 3281 independent human summaries. Inspired by existing pyramid-based evaluation approaches, the AutoMUP (Automatic Meaning Unit Pyramid) method is proposed, which extracts consensus-based content from multiple human summaries. AutoMUP clusters the meaning units extracted from human summaries using embedding, statistically models inter-participant agreement, and generates graded summaries based on consensus weight. In this framework, the gold summary corresponds to the highest-consensus AutoMUP configuration, constructed from the most frequently supported meaning units across human summaries. Experimental results show that AutoMUP summaries exhibit high semantic overlap with robust LLM summaries such as Flash 2.5 and GPT-5.1. Furthermore, ablation studies clearly demonstrate the decisive role of consensus weight and clustering in determining summary quality. The proposed approach can be generalized to other Turkic languages at low cost."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="egin-onan-2026-tr">
<titleInfo>
<title>TR-EduVSum: A Turkish-Focused Dataset and Consensus Framework for Educational Video Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Figen</namePart>
<namePart type="family">Eğin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aytuğ</namePart>
<namePart type="family">Onan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kemal</namePart>
<namePart type="family">Oflazer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullatif</namePart>
<namePart type="family">Köksal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Onur</namePart>
<namePart type="family">Varol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-370-8</identifier>
</relatedItem>
<abstract>This study presents a framework for generating the gold-standard summary fully automatically and reproducibly based on multiple human summaries of Turkish educational videos. Within the scope of the study, a new dataset called TR-EduVSum was created, encompassing 82 Turkish course videos in the field of “Data Structures and Algorithms” and containing a total of 3281 independent human summaries. Inspired by existing pyramid-based evaluation approaches, the AutoMUP (Automatic Meaning Unit Pyramid) method is proposed, which extracts consensus-based content from multiple human summaries. AutoMUP clusters the meaning units extracted from human summaries using embedding, statistically models inter-participant agreement, and generates graded summaries based on consensus weight. In this framework, the gold summary corresponds to the highest-consensus AutoMUP configuration, constructed from the most frequently supported meaning units across human summaries. Experimental results show that AutoMUP summaries exhibit high semantic overlap with robust LLM summaries such as Flash 2.5 and GPT-5.1. Furthermore, ablation studies clearly demonstrate the decisive role of consensus weight and clustering in determining summary quality. The proposed approach can be generalized to other Turkic languages at low cost.</abstract>
<identifier type="citekey">egin-onan-2026-tr</identifier>
<location>
<url>https://aclanthology.org/2026.sigturk-1.5/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>52</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TR-EduVSum: A Turkish-Focused Dataset and Consensus Framework for Educational Video Summarization
%A Eğin, Figen
%A Onan, Aytuğ
%Y Oflazer, Kemal
%Y Köksal, Abdullatif
%Y Varol, Onur
%S Proceedings of the Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-370-8
%F egin-onan-2026-tr
%X This study presents a framework for generating the gold-standard summary fully automatically and reproducibly based on multiple human summaries of Turkish educational videos. Within the scope of the study, a new dataset called TR-EduVSum was created, encompassing 82 Turkish course videos in the field of “Data Structures and Algorithms” and containing a total of 3281 independent human summaries. Inspired by existing pyramid-based evaluation approaches, the AutoMUP (Automatic Meaning Unit Pyramid) method is proposed, which extracts consensus-based content from multiple human summaries. AutoMUP clusters the meaning units extracted from human summaries using embedding, statistically models inter-participant agreement, and generates graded summaries based on consensus weight. In this framework, the gold summary corresponds to the highest-consensus AutoMUP configuration, constructed from the most frequently supported meaning units across human summaries. Experimental results show that AutoMUP summaries exhibit high semantic overlap with robust LLM summaries such as Flash 2.5 and GPT-5.1. Furthermore, ablation studies clearly demonstrate the decisive role of consensus weight and clustering in determining summary quality. The proposed approach can be generalized to other Turkic languages at low cost.
%U https://aclanthology.org/2026.sigturk-1.5/
%P 52-60
Markdown (Informal)
[TR-EduVSum: A Turkish-Focused Dataset and Consensus Framework for Educational Video Summarization](https://aclanthology.org/2026.sigturk-1.5/) (Eğin & Onan, SIGTURK 2026)
ACL