MLASK: Multimodal Summarization of Video-based News Articles

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10476790" target="_blank" >RIV/00216208:11320/23:10476790 - isvavai.cz</a>

Výsledek na webu

<a href="http://hdl.handle.net/11234/1-5135" target="_blank" >http://hdl.handle.net/11234/1-5135</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

MLASK: Multimodal Summarization of Video-based News Articles

Popis výsledku v původním jazyce

In recent years, the pattern of news consumption has been changing. The most popular multimedia news formats are now multimodal - the reader is often presented not only with a textual article but also with a short, vivid video. To draw the attention of the reader, such video-based articles are usually presented as a short textual summary paired with an image thumbnail.In this paper, we introduce MLASK (MultimodaL Article Summarization Kit) - a new dataset of video-based news articles paired with a textual summary and a cover picture, all obtained by automatically crawling several news websites. We demonstrate how the proposed dataset can be used to model the task of multimodal summarization by training a Transformer-based neural model. We also examine the effects of pre-training when the usage of generative pre-trained language models helps to improve the model performance, but (additional) pre-training on the simpler task of text summarization yields even better results. Our experiments suggest that the benefits of pre-training and using additional modalities in the input are not orthogonal.

Název v anglickém jazyce

MLASK: Multimodal Summarization of Video-based News Articles

Popis výsledku anglicky

In recent years, the pattern of news consumption has been changing. The most popular multimedia news formats are now multimodal - the reader is often presented not only with a textual article but also with a short, vivid video. To draw the attention of the reader, such video-based articles are usually presented as a short textual summary paired with an image thumbnail.In this paper, we introduce MLASK (MultimodaL Article Summarization Kit) - a new dataset of video-based news articles paired with a textual summary and a cover picture, all obtained by automatically crawling several news websites. We demonstrate how the proposed dataset can be used to model the task of multimodal summarization by training a Transformer-based neural model. We also examine the effects of pre-training when the usage of generative pre-trained language models helps to improve the model performance, but (additional) pre-training on the simpler task of text summarization yields even better results. Our experiments suggest that the benefits of pre-training and using additional modalities in the input are not orthogonal.

Druh

R - Software

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

2023

Kód důvěrnosti údajů

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

Interní identifikační kód produktu

https://github.com/ufal/MLASK

Technické parametry

Výsledek je volně dostupný na adrese: http://hdl.handle.net/11234/1-5135

Ekonomické parametry

50.000 Kč

IČO vlastníka výsledku

00216208

Název vlastníka

Univerzita Karlova v Praze