OpenNMT: Neural Machine Translation Toolkit
arXiv:1805.11462
Abstract
OpenNMT is an open-source toolkit for neural machine translation (NMT). The system prioritizes efficiency, modularity, and extensibility with the goal of supporting NMT research into model architectures, feature representations, and source modalities, while maintaining competitive performance and reasonable training requirements. The toolkit consists of modeling and translation support, as well as detailed pedagogical documentation about the underlying techniques. OpenNMT has been used in several production MT systems, modified for numerous research papers, and is implemented across several deep learning frameworks.
arXiv commentPresentation to AMTA 2018 - Boston. arXiv admin note: substantial text overlap with arXiv:1701.02810
References in corpus (18)
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Convolutional Sequence to Sequence Learning
- A Neural Conversational Model
- Effective Approaches to Attention-based Neural Machine Translation
- From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Listen, Attend and Spell
- Sockeye: A Toolkit for Neural Machine Translation
- Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations
- Massive Exploration of Neural Machine Translation Architectures
- Challenges in Data-to-Document Generation
- Effective Strategies in Zero-Shot Neural Machine Translation
- Toward a full-scale neural machine translation in production: the Booking.com use case
- OSU Multimodal Machine Translation System Report
Cited by in corpus (5)
- Distilling Knowledge Learned in BERT for Text Generation
- PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions
- Tigrinya Neural Machine Translation with Transfer Learning for Humanitarian Response
- Korean-to-Chinese Machine Translation using Chinese Character as Pivot Clue
- Improving Scientific Article Visibility by Neural Title Simplification