Multimodal Neural Machine Translation: A Survey of the State of the Art
Zhejiang University, Shanghai Artificial Intelligence Laboratory, Tsinghua University, Peking University, Universität Bern, Copenhagen University, University of Sheffield, Indian Institute of Technology Kharagpur, Dhirubhai Ambani Institute Of Information and Communication Technology, Indian Institute of Technology, Kanpur, Dhirubhai Ambani Institute Of Information and Communication Technology, Dalian University of Technology, Shandong University, Renmin University of China, Carnegie Mellon University, Chinese Academy of Sciences, University of Illinois at Urbana-Champaign, Jilin University, Harbin Institute of Technology, Indian Institute of Technology Kharagpur, Chulalongkorn University, Nankai University, Tata Consultancy Services Limited, India, International University of Rabat, Gwangju Institute of Science and Technology, Indian Institute of Science Education and Research Kolkata, University of Technology Sydney, Seoul National University, University of Seoul, Georgetown University, Monash University, Hong Kong University of Science and Technology, Lancaster University, Korea Advanced Institute of Science & Technology, Universidad Nacional Autónoma de México, National Technical University of Athens, Shanghai Maritime University, Athens University of Economics and Business, Higher School of Economics, Warsaw School of Economics, Korea University, University of Auckland, University of Cambridge, Kathmandu University, Dwarkadas J. Sanghvi College Of Engineering, Dhirubhai Ambani Institute Of Information and Communication Technology, SUN YAT-SEN UNIVERSITY, Pohang University of Science and Technology, Télécom ParisTech, Beijing University of Aeronautics and Astronautics, University of Houston, Shanghai University, Fudan University, Northeast Forest University, Keio University, Tokyo Institute of Technology, Université Laval, Chongqing University, University of Zurich, Technical University of Munich, ORRO AI Genius LLC, Sichuan University, University of Science and Technology of China, University of Delhi, University of New South Wales, Visvesvaraya National Institute of Technology, The Hong Kong University of Science and Technology, Indian Institute of Science Education and Research, symbiosis Law School, Ruhr-Universität Bochum, Johann Wolfgang Goethe Universität Frankfurt am Main, University of Winnipeg, National Institute of Technology Karnataka, National Institute of Technology, SRM Institute of Science and Technology, University of South Carolina, Indian Institute of Technology Bombay, Indian Institute of Technology, Bombay, Indian Institute of Technology, Roorkee, Dhirubhai Ambani Institute Of Information and Communication Technology, HES-SO : UAS Western Switzerland, Neur.on, University of Fribourg, University of Geneva, Seoul National University, New York University, Yonsei University, Fujitsu Research and Development Center Co. Ltm., Alibaba Group, Tencent AI Lab, Baidu, Huawei Technologies Ltd., Thunisoft, PKU Law, Xiaomi Corporation, JD.com, ByteDance Inc., IFLYTEK CO.LTD., Shanghai Artificial Intelligence Laboratory, China Judicial Big Data Research Institute Co., Ltd, PowerLaw, ETHZ - ETH Zurich, Sung Kyun Kwan University, Ewha Women’s University, Huazhong University of Science and Technology and Nanjing University · nanjing university
PDF 由论文原始站点提供,PaperCompass 不保存论文文件。DOI 10.18653/v1/2025.emnlp-main.1125 ↗
摘要
Multimodal neural machine translation (MNMT) has received increasing attention due to its widespread applications in various fields such as cross-border e-commerce and cross-border social media platforms. The task aims to integrate other modalities, such as the visual modality, with textual data to enhance translation performance. We survey the major milestones in MNMT research, providing a comprehensive overview of relevant datasets and recent methodologies, and discussing key challenges and promising research directions.