On Using Monolingual Corpora in Neural Machine Translation
Explore this paper's citation graph
Summary
This work investigates how to leverage abundant monolingual corpora for neural machine translation to improve results for En-Fr and En-De translation and extends to high resource languages such as Cs-En and De-En.
- Type
- preprint
- Published
- 2015-03-11
- Cited by
- 593
- References
- 33
- Access
- Open access
- OpenAlex
- https://openalex.org/W1915251500
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:15352384
Keywords
Machine translation, BLEU, Computer science, Leverage (statistics), Artificial intelligence
References
- ADADELTA: An Adaptive Learning Rate Method
- Theano: new features and speed improvements
- Recurrent Continuous Translation Models
- On the difficulty of training recurrent neural networks
- Improving neural networks by preventing co-adaptation of feature detectors
- Continuous space language models
- Long Short-Term Memory
- On Using Very Large Target Vocabulary for Neural Machine Translation
- Practical Variational Inference for Neural Networks
- Addressing the Rare Word Problem in Neural Machine Translation
- Moses: Open Source Toolkit for Statistical Machine Translation
- Bidirectional recurrent neural networks
- A Hierarchical Phrase-Based Model for Statistical Machine Translation
- Statistical Phrase-Based Translation
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
- WIT3: Web Inventory of Transcribed and Translated Talks
- Continuous Space Translation Models for Phrase-Based Statistical Machine Translation
- Fast and Robust Neural Network Joint Models for Statistical Machine Translation
- Maxout Networks
- RNNLM - Recurrent Neural Network Language Modeling Toolkit
Cited by
- Attention-Based Models for Speech Recognition
- Describing Multimedia Content Using Attention-Based Encoder-Decoder Networks
- A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition
- End-to-end attention-based large vocabulary speech recognition
- Natural Language Video Description using Deep Recurrent Neural Networks
- Minimum Risk Training for Neural Machine Translation
- Mutual Information and Diverse Decoding Improve Neural Machine Translation
- Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism
- Montreal Neural Machine Translation Systems for WMT’15
- Improving Neural Machine Translation Models with Monolingual Data
- Neural Summarization by Extracting Sentences and Words
- Adaptation of Language Models for SMT Using Neural Networks with Topic Information
- Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text
- Sentence-Level Grammatical Error Identification as Sequence-to-Sequence Correction
- Variational Neural Machine Translation
- Linguistic Input Features Improve Neural Machine Translation
- Generalizing and Hybridizing Count-based and Neural Language Models
- Captioning Images with Diverse Objects
- A Neural Knowledge Language Model
- WMT 2016 Multimodal Translation System Description based on Bidirectional Recurrent Neural Networks with Double-Embeddings
Related papers
- Better Evaluation Metrics Lead to Better Machine Translation
- Statistical Machine Translation with Rule based Machine Translation
- Neural Machine Translation of Indian Languages
- Factored Statistical Machine Translation for German-English
- Phrase-based Chinese Mongolian statistical machine translation
- Improving English-to-Indian Language Neural Machine Translation Systems
- Very Deep Transformers for Neural Machine Translation
- A Novel Hybrid Approach to Improve Neural Machine Translation Decoding using Phrase-Based Statistical Machine Translation