Neural Monkey: An Open-source Tool for Sequence Learning

By Jindřich Helcl, Jindřich Libovický. 2017

71 citations recorded by the source corpus.

Abstract In this paper, we announce the development of Neural Monkey – an open-source neural machine translation (NMT) and general sequence-to-sequence learning system built over the TensorFlow machine learning library. The system provides a high-level API tailored for fast prototyping of complex architectures with multiple sequence encoders and decoders. Models’ overall architecture is specified in easy-to-read configuration files. The long-term goal of the Neural Monkey project is to create and maintain a growing collection of implementations of recently proposed components or methods, and therefore it is designed to be easily extensible. Trained models can be deployed either for batch data processing or as a web service. In the presented paper, we describe the design of the system and introduce the reader to running experiments using Neural Monkey.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Machine Translation, ML Systems & Hardware

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

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Machine Translation

In ML Systems & Hardware

Citations in the corpus

Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning (2018, methodology): “5The code is available in the Neural Monkey fork https://github.com/juliakreutzer/ bandit-neuralmonkey/tree/acl2018.”
Graph Convolutional Encoders for Syntax-aware Neural Machine Translation (2017, methodology): “Experiments are performed using the Neural Mon-key toolkit 3 (Helcl and Libovick´y, 2017), which implements the model of Bahdanau et al. (2015) in TensorFlow.”
Results of the WMT17 Metrics Shared Task (2017, methodology): “NMT Training Task systems are all instances of Neural Monkey (Helcl and Libovick´y, 2017) implementing the To match the format of the newstest where all MT systems translate all sentences, we selected such subsets of sentences from HUME Test Set Round 2.”
Evaluating the morphological competence of Machine Translation Systems (2017, methodology): “• BPE-based NMT: LIMSI NMT (Burlot et al., 2017) is based on NMTPY (Caglayan et al., 2017), UEDIN NMT (Sennrich et al., 2017a) on Nematus (Sennrich et al., 2017b) and UFAL NMT (Bojar et al., 2017b) on Neural Monkey (Helcl and Libovick´y, 2017).”
End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification (2018, methodology): “The experiments were conducted using Neural Monkey 1 (Helcl and Libovick´y, 2017).”
Neural Machine Translation: A Review (2019, unknown): “Non- or partially autoregressive NMT which aims to reduce or remove the sequential dependency on the translation prefix inside the decoder for enhanced parallelizability has been studied by Wang et al. (2018a), Gu et al. (2017a), Guo et al. (2018), Wang et al. (2019), Libovický and Helcl (2018), Lee”
Unsupervised Pretraining for Neural Machine Translation Using Elastic Weight Consolidation (2019, methodology): “The model implementation is available in Neural Monkey3 (Helcl and Libovický, 2017) framework for sequence-to-sequence modeling.”
Debugging Neural Machine Translations (2018, methodology): “NMT frameworks like Nematus [15], Neural Monkey [4] or OpenNMT [7] have some forms of visualization, but they mainly handle representation of the translation process instead of the translation results.”
Are BLEU and Meaning Representation in Opposition? (2018, methodology): “The de models were trained on the Multi30K multilingual image caption dataset (Elliott et al., 2016), extended by Helcl and Libovick´y (2017b), who acquired additional parallel data using back-translation (Sennrich et al., 2016) and perplexity-based selection (Yasuda et al., 2008).”