We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via continuous learning. NMT-Keras is based on an extended version of the popular Keras library, and it runs on Theano and Tensorflow. State-of-the-art neural machine translation models are deployed and used following the high-level framework provided by Keras. Given its high modularity and flexibility, it also has been extended to tackle different problems, such as image and video captioning, sentence classification and visual question answering.
THUMT: An Open Source Toolkit for Neural Machine Translation
Tsinghua University(清华大学);Jiangsu Collaborative Innovation Center for Language Competence(江苏语言能力协同创新中心);Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院)
XNMT: The eXtensible Neural Machine Translation Toolkit
Carnegie Mellon University(卡内基梅隆大学);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);LIMSI/CNRS/Université Paris-Saclay(巴黎萨克雷大学LIMSI/法国国家科学研究中心);University of Pennsylvania(宾夕法尼亚大学);ENS/CNRS/EHESS/INRIA(巴黎高等师范学院/法国国家科学研究中心/巴黎高等经济社会学院/法国国家信息与自动化研究所);University of Illinois(伊利诺伊大学)
An Empirical Study of Mini-Batch Creation Strategies for Neural Machine Translation
NTT Communication Science Laboratories, NTT Corporation(NTT株式会社NTT通信科学基础研究所);Nara Institute of Science and Technology(奈良先端科学技术大学院大学);Carnegie Mellon University(卡内基梅隆大学);Japan Science and Technology Agency(日本科学技术振兴机构)
University of Engineering and Technology - Hanoi VNU(河内越南国家大学工程技术大学);University of Information and Communication Technology - Thai Nguyen University(太原大学信息与通信技术大学);University of Economics-Technical For Industries(工业经济技术大学)