Towards Unified Uni- and Multi-modal News Headline Generation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492875" target="_blank" >RIV/00216208:11320/24:10492875 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2024.findings-eacl.30.pdf" target="_blank" >https://aclanthology.org/2024.findings-eacl.30.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Towards Unified Uni- and Multi-modal News Headline Generation

Popis výsledku v původním jazyce

Thanks to the recent progress in vision-language modeling and the evolving nature of news consumption, the tasks of automatic summarization and headline generation based on multimodal news articles have been gaining popularity. One of the limitations of the current approaches is caused by the commonly used sophisticated modular architectures built upon hierarchical cross-modal encoders and modality-specific decoders, which restrict the model&apos;s applicability to specific data modalities - once trained on, e.g., text+video pairs there is no straightforward way to apply the model to text+image or text-only data. In this work, we propose a unified task formulation that utilizes a simple encoder-decoder model to generate headlines from uni- and multi-modal news articles. This model is trained jointly on data of several modalities and extends the textual decoder to handle the multimodal output.

Název v anglickém jazyce

Towards Unified Uni- and Multi-modal News Headline Generation

Popis výsledku anglicky

Thanks to the recent progress in vision-language modeling and the evolving nature of news consumption, the tasks of automatic summarization and headline generation based on multimodal news articles have been gaining popularity. One of the limitations of the current approaches is caused by the commonly used sophisticated modular architectures built upon hierarchical cross-modal encoders and modality-specific decoders, which restrict the model&apos;s applicability to specific data modalities - once trained on, e.g., text+video pairs there is no straightforward way to apply the model to text+image or text-only data. In this work, we propose a unified task formulation that utilizes a simple encoder-decoder model to generate headlines from uni- and multi-modal news articles. This model is trained jointly on data of several modalities and extends the textual decoder to handle the multimodal output.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GX19-26934X" target="_blank" >GX19-26934X: Neuronové reprezentace v multimodálním a mnohojazyčném modelování</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Findings of the Association for Computational Linguistics: EACL 2024

ISBN

979-8-89176-093-6

ISSN

—

e-ISSN

—

Počet stran výsledku

14

Strana od-do

437-450

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

St. Julians, Malta

Datum konání akce

17. 3. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—