Apologies for cross-posting ------------------------------------------------------ Dear colleagues, We invite you to submit to the first edition of our workshop on "Linguistic Insights from and for Multimodal Language Processing" that will be co-located with KONVENS 2023 in Ingolstadt. The deadline is extended by a week until July 14th, 2023. We are looking forward to your contribution. Our website is available at https://sites.google.com/view/limo2023/home Please find the last CfP below. Best wishes, LIMO 2023 organizers ------------------------------------------------------ Last Call for Papers: Linguistic Insights from and for Multimodal Language Processing @KONVENS 2023 Processing multimodal information (like visual representations of the environment, auditory cues, images, gestures, gaze etc.) and integrating them is a constant and effortless process in human language processing. Recent progress in the area of language & vision, large-scale visually grounded language models, and multimodal learning have led to breakthroughs in challenging multimodal NLP applications like image–text retrieval, image captioning or visual question answering. Yet, modeling the semantics and pragmatics of situated language understanding and generation and, generally, language processing beyond the linguistic context, i.e. in combination with multiple other modalities, is still one of the biggest challenges in NLP and Computational Linguistics. While there have been recent venues and workshops targeting multimodal representation learning and large-scale Language and Vision models, there is a lack of discussion in the community that focuses on linguistic multimodal phenomena, domain- and task-specific analyses of multimodality and, generally, contributions of computational linguistics to multimodal learning and vice versa.  With this workshop, we aim to bring together researchers who work on various linguistic aspects of multimodal language processing to discuss and share the recent advances in this interdisciplinary field. Topics of interest:     ▪    New multimodal datasets and training schemes in text and dialogue     ▪    Multimodal tasks and frameworks in CL     ▪    Annotation of multimodal datasets     ▪    Modeling and analysis of linguistic phenomena in multimodal datasets     ▪    Analysis and discussion of shortcomings of existing multimodal language models     ▪    Approaches to multimodality in different domains, e.g., documents, social media, visual dialogue, situated dialogue, etc.     ▪    Work on cross-modal and inter-modal representations, relationships, and dependencies     ▪    Opinion pieces and (theoretical) reflections on multimodality in NLP/Computational Linguistics Keynote Speakers --------------- Sandro Pezzelle, University of Amsterdam Letitia Parcalabescu, Heidelberg University Important Dates --------------- July 14, 2023     – Paper Submission Deadline (Extended) August 21, 2023     – Notification of Acceptance September 04, 2023     – Camera-ready Deadline September 22, 2023     – Workshop Day (one of these days) * All deadlines are 11:59 PM UTC-12:00 ("anywhere on Earth") Paper Submission: ----------------- All paper submissions must use the official KONVENS 2023 style templates.     ▪    Long papers must not exceed eight (8) pages of content.     ▪    Short papers and demonstration papers must not exceed four (4) pages of content.     ▪    Non-archival abstracts must not exceed one (1) page. Organizers: --------------- Piush Aggarwal, FernUniversität in Hagen, piush.aggarwal@fernuni-hagen.de Özge Alaçam, Universität Bielefeld, oezge.alacam@uni-bielefeld.de Carina Silberer, Universität Stuttgart, carina.silberer@ims.uni-stuttgart.de Sina Zarrieß, Universität Bielefeld, sina.zarriess@uni-bielefeld.de Torsten Zesch, FernUniversität in Hagen, torsten.zesch@fernuni-hagen.de Contact: --------- Özge Alaçam (oezge.alacam@uni-bielefeld.de), Piush Aggarwal (piush.aggarwal@fernuni-hagen.de) Workshop webpage: https://sites.google.com/view/limo2023/home KONVENS 2023 webpage: https://www.thi.de/konvens-2023/