{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-embedding-for-spatial-role-labeling","title":"Deep Embedding for Spatial Role Labeling","arxiv_id":"1603.08474","date":"2016-03-28","proceeding":null,"authors":["Oswaldo Ludwig","Xiao Liu","Parisa Kordjamshidi","Marie-Francine Moens"],"abstract":"This paper introduces the visually informed embedding of word (VIEW), a\ncontinuous vector representation for a word extracted from a deep neural model\ntrained using the Microsoft COCO data set to forecast the spatial arrangements\nbetween visual objects, given a textual description. The model is composed of a\ndeep multilayer perceptron (MLP) stacked on the top of a Long Short Term Memory\n(LSTM) network, the latter being preceded by an embedding layer. The VIEW is\napplied to transferring multimodal background knowledge to Spatial Role\nLabeling (SpRL) algorithms, which recognize spatial relations between objects\nmentioned in the text. This work also contributes with a new method to select\ncomplementary features and a fine-tuning method for MLP that improves the $F1$\nmeasure in classifying the words into spatial roles. The VIEW is evaluated with\nthe Task 3 of SemEval-2013 benchmark data set, SpaceEval.","url_abs":"http://arxiv.org/abs/1603.08474v1","url_pdf":"http://arxiv.org/pdf/1603.08474v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-embedding-for-spatial-role-labeling","repo_url":"https://github.com/oswaldoludwig/visually-informed-embedding-of-word-VIEW-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1603.08474","atlas_url":"https://app.syntology.ai/?focus=1603.08474","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}