@inproceedings{ai-etal-2026-mosaic,
title = "{MOSAIC}: A Large-Scale Multimodal Open-Course Segmentation and Alignment Corpus in {C}hinese",
author = "Ai, Yuming and
Fan, Shuai and
Xu, Hua and
Kong, Fang",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.246/",
pages = "5176--5195",
ISBN = "979-8-89176-462-0",
abstract = "Real-world lectures follow a predefined topic inventory (e.g., a syllabus), but instructors often reorder, paraphrase, or skip items, creating mismatches between the outline and the spoken content. Lectures also contain non-topical utterances (openings, transitions and wrap-ups) that should not be assigned to any topic, yet existing corpora rarely model both challenges. We present **MOSAIC** (**M**ultimodal **O**pen-course **S**egmentation and **A**lignment corpus **I**n **C**hinese), a large-scale Chinese MOOC corpus for *topic-guided segmentation and alignment* under predefined inventories, with explicit *non-topical* labels and matched slide resources. MOSAIC includes **MOSAIC-G** (human-annotated gold benchmark with utterance-level topic alignment and video-level links to matched slide resources) and **MOSAIC-S** (automatically labeled silver data), collectively covering 179 courses and 14,942 videos. To scale annotation, we propose **DORA** (**D**ual-stage **O**utline **R**efinement and **A**lignment), a two-stage pipeline that refines noisy inventories and then performs joint segmentation and topic assignment. Experiments show that silver supervision substantially improves the performance of local models and that incorporating slides consistently benefits knowledge-point extraction, a lecture-comprehension proxy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ai-etal-2026-mosaic">
<titleInfo>
<title>MOSAIC: A Large-Scale Multimodal Open-Course Segmentation and Alignment Corpus in Chinese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuming</namePart>
<namePart type="family">Ai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fang</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Real-world lectures follow a predefined topic inventory (e.g., a syllabus), but instructors often reorder, paraphrase, or skip items, creating mismatches between the outline and the spoken content. Lectures also contain non-topical utterances (openings, transitions and wrap-ups) that should not be assigned to any topic, yet existing corpora rarely model both challenges. We present **MOSAIC** (**M**ultimodal **O**pen-course **S**egmentation and **A**lignment corpus **I**n **C**hinese), a large-scale Chinese MOOC corpus for *topic-guided segmentation and alignment* under predefined inventories, with explicit *non-topical* labels and matched slide resources. MOSAIC includes **MOSAIC-G** (human-annotated gold benchmark with utterance-level topic alignment and video-level links to matched slide resources) and **MOSAIC-S** (automatically labeled silver data), collectively covering 179 courses and 14,942 videos. To scale annotation, we propose **DORA** (**D**ual-stage **O**utline **R**efinement and **A**lignment), a two-stage pipeline that refines noisy inventories and then performs joint segmentation and topic assignment. Experiments show that silver supervision substantially improves the performance of local models and that incorporating slides consistently benefits knowledge-point extraction, a lecture-comprehension proxy.</abstract>
<identifier type="citekey">ai-etal-2026-mosaic</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.246/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>5176</start>
<end>5195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MOSAIC: A Large-Scale Multimodal Open-Course Segmentation and Alignment Corpus in Chinese
%A Ai, Yuming
%A Fan, Shuai
%A Xu, Hua
%A Kong, Fang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ai-etal-2026-mosaic
%X Real-world lectures follow a predefined topic inventory (e.g., a syllabus), but instructors often reorder, paraphrase, or skip items, creating mismatches between the outline and the spoken content. Lectures also contain non-topical utterances (openings, transitions and wrap-ups) that should not be assigned to any topic, yet existing corpora rarely model both challenges. We present **MOSAIC** (**M**ultimodal **O**pen-course **S**egmentation and **A**lignment corpus **I**n **C**hinese), a large-scale Chinese MOOC corpus for *topic-guided segmentation and alignment* under predefined inventories, with explicit *non-topical* labels and matched slide resources. MOSAIC includes **MOSAIC-G** (human-annotated gold benchmark with utterance-level topic alignment and video-level links to matched slide resources) and **MOSAIC-S** (automatically labeled silver data), collectively covering 179 courses and 14,942 videos. To scale annotation, we propose **DORA** (**D**ual-stage **O**utline **R**efinement and **A**lignment), a two-stage pipeline that refines noisy inventories and then performs joint segmentation and topic assignment. Experiments show that silver supervision substantially improves the performance of local models and that incorporating slides consistently benefits knowledge-point extraction, a lecture-comprehension proxy.
%U https://aclanthology.org/2026.findings-emnlp.246/
%P 5176-5195
Markdown (Informal)
[MOSAIC: A Large-Scale Multimodal Open-Course Segmentation and Alignment Corpus in Chinese](https://aclanthology.org/2026.findings-emnlp.246/) (Ai et al., Findings 2026)
ACL