{"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/bridge-correlational-neural-networks-for","title":"Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning","arxiv_id":"1510.03519","date":"2015-10-13","proceeding":"NAACL 2016 6","authors":["Janarthanan Rajendran","Mitesh M. Khapra","Sarath Chandar","Balaraman Ravindran"],"abstract":"Recently there has been a lot of interest in learning common representations\nfor multiple views of data. Typically, such common representations are learned\nusing a parallel corpus between the two views (say, 1M images and their English\ncaptions). In this work, we address a real-world scenario where no direct\nparallel data is available between two views of interest (say, $V_1$ and $V_2$)\nbut parallel data is available between each of these views and a pivot view\n($V_3$). We propose a model for learning a common representation for $V_1$,\n$V_2$ and $V_3$ using only the parallel data available between $V_1V_3$ and\n$V_2V_3$. The proposed model is generic and even works when there are $n$ views\nof interest and only one pivot view which acts as a bridge between them. There\nare two specific downstream applications that we focus on (i) transfer learning\nbetween languages $L_1$,$L_2$,...,$L_n$ using a pivot language $L$ and (ii)\ncross modal access between images and a language $L_1$ using a pivot language\n$L_2$. Our model achieves state-of-the-art performance in multilingual document\nclassification on the publicly available multilingual TED corpus and promising\nresults in multilingual multimodal retrieval on a new dataset created and\nreleased as a part of this work.","url_abs":"http://arxiv.org/abs/1510.03519v3","url_pdf":"http://arxiv.org/pdf/1510.03519v3.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":"bridge-correlational-neural-networks-for","repo_url":"https://github.com/adobe-research/Cross-lingual-Test-Dataset-XTD10","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1510.03519","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}