@misc{NguyenLoRaLayMultilingualMultimodal2023,
 abstract = {Text Summarization is a popular task and an active area of research for the Natural Language Processing community. By definition, it requires to account for long input texts, a characteristic which poses computational challenges for neural models. Moreover, real-world documents come in a variety of complex, visually-rich, layouts. This information is of great relevance, whether to highlight salient content or to encode long-range interactions between textual passages. Yet, all publicly available summarization datasets only provide plain text content. To facilitate research on how to exploit visual/layout information to better capture long-range dependencies in summarization models, we present LoRaLay, a collection of datasets for long-range summarization with accompanying visual/layout information. We extend existing and popular English datasets (arXiv and PubMed) with layout information and propose four novel datasets -- consistently built from scholar resources -- covering French, Spanish, Portuguese, and Korean languages. Further, we propose new baselines merging layout-aware and long-range models -- two orthogonal approaches -- and obtain state-of-the-art results, showing the importance of combining both lines of research.},
 author = {Nguyen, Laura and Scialom, Thomas and Piwowarski, Benjamin and Staiano, Jacopo},
 copyright = {All rights reserved},
 doi = {10.48550/arXiv.2301.11312},
 month = {January},
 note = {arXiv:2301.11312 [cs]},
 publisher = {arXiv},
 shorttitle = {{LoRaLay}},
 title = {{LoRaLay}: {A} {Multilingual} and {Multimodal} {Dataset} for {Long} {Range} and {Layout}-{Aware} {Summarization}},
 url = {http://arxiv.org/abs/2301.11312},
 urldate = {2023-03-27},
 year = {2023}
}