@inproceedings{NguyenLoRaLayMultilingualMultimodal2023a,
 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.},
 address = {Dubrovnik, Croatia},
 author = {Nguyen, Laura and Scialom, Thomas and Piwowarski, Benjamin and Staiano, Jacopo},
 booktitle = {Proceedings of the 17th {Conference} of the {European} {Chapter} of the {Association} for {Computational} {Linguistics}},
 copyright = {All rights reserved},
 month = {May},
 pages = {636--651},
 publisher = {Association for Computational Linguistics},
 shorttitle = {{LoRaLay}},
 title = {{LoRaLay}: {A} {Multilingual} and {Multimodal} {Dataset} for {Long} {Range} and {Layout}-{Aware} {Summarization}},
 url = {https://aclanthology.org/2023.eacl-main.46},
 urldate = {2023-09-01},
 year = {2023}
}