Neural Machine Translation: A Review
By Felix Stahlberg. 2019
429 citations recorded by the source corpus.
The field of machine translation (MT), the automatic translation of written text from one natural language into another, has experienced a major paradigm shift in recent years. Statistical MT, which mainly relies on various count-based models and which used to dominate MT research for decades, has largely been superseded by neural machine translation (NMT), which tackles translation with a single neural network. In this work we will trace back the origins of modern NMT architectures to word and sentence embeddings and earlier examples of the encoder-decoder network family. We will conclude with a short survey of more recent trends in the field.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Adam Santoro
- Stefan Wermter
- Andrew Kyle Lampinen
- Timothy P. Lillicrap
- Sergey Levine
- Cornelius Weber
- Jindong Wang
- Yue Cao
Citations in the corpus
- Continual Learning for Neural Machine Translation (2021, methodology): “NMT systems are sensitive to the data distributions (Stahlberg, 2019).”
- PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization (2023, background): “Large language models (LLMs) have attracted increasing attention in the field of artificial intelligence [1, 2, 3, 4, 5, 6], with various applications from question answering [7, 8], machine translation [9, 10] to content creation [11, 12].”
- Neural Machine Translation for Low-resource Languages: A Survey (2021, background): “Some of the previous survey papers discussed different NMT architectures [149, 172, 184, 200, 208].”
- Survey on reinforcement learning for language processing (2021, background): “Neural Machine Translation (NMT) [121] uses large neural networks to predict the likelihood of a sequence of words.”
- Symbolic Behaviour in Artificial Intelligence (2021, background): “When fully trained on translation [70], programming [69], or mathematics (see 2), transformers substantially outperform existing symbolic or hybrid models.”