Skip to search formSkip to main contentSkip to account menu

Incorporating Copying Mechanism in Sequence-to-Sequence Learning

This paper incorporates copying into neural network-based Seq2Seq learning and proposes a new model called CopyNet with encoder-decoder structure which can nicely integrate the regular way of word generation in the decoder with the new copying mechanism which can choose sub-sequences in the input sequence and put them at proper places in the output sequence.
View on ACL (opens in a new tab)

Non-Autoregressive Neural Machine Translation

A model is introduced that avoids this autoregressive property and produces its outputs in parallel, allowing an order of magnitude lower latency during inference, and achieves near-state-of-the-art performance on WMT 2016 English-Romanian.
View PDF on arXiv (opens in a new tab)

Learning to Translate in Real-time with Neural Machine Translation

A neural machine translation (NMT) framework for simultaneous translation in which an agent learns to make decisions on when to translate from the interaction with a pre-trained NMT environment is proposed.
View on ACL (opens in a new tab)

Universal Neural Machine Translation for Extremely Low Resource Languages

The proposed approach utilizing a transfer-learning approach to share lexical and sentence level representations across multiple source languages into one target language is able to achieve 23 BLEU on Romanian-English WMT2016 using a tiny parallel corpus of 6k sentences.
View on ACL (opens in a new tab)

Search Engine Guided Neural Machine Translation

An attention-based neural machine translation model is extended by allowing it to access an entire training set of parallel sentence pairs even after training, and significantly outperforms the baseline approach.
View via Publisher (opens in a new tab)

Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations

This work addresses the degeneracy problem due to capturing spurious correlations by quantitatively analyzing the mutual information between language IDs of the source and decoded sentences and proposes two simple but effective approaches: decoder pre-training; back-translation.
View on ACL (opens in a new tab)

Meta-Learning for Low-Resource Neural Machine Translation

The proposed model-agnostic meta-learning algorithm for low-resource neural machine translation (NMT) is extended and significantly outperforms the multilingual, transfer learning based approach and enables us to train a competitive NMT system with only a fraction of training examples.
View on ACL (opens in a new tab)

Online False Data Injection Attack Detection With Wavelet Transform and Deep Neural Networks

A new false data injection attack detection mechanism for ac state estimation that can effectively capture inconsistency by analyzing temporally consecutive estimated system states using wavelet transform and deep neural network techniques is proposed.
View on IEEE (opens in a new tab)

A Teacher-Student Framework for Zero-Resource Neural Machine Translation

This paper proposes a method for zero-resource NMT by assuming that parallel sentences have close probabilities of generating a sentence in a third language on a source-pivot parallel corpus.
View on ACL (opens in a new tab)

Search Engine Guided Non-Parametric Neural Machine Translation

Empirical evaluation of an attention-based neural machine translation model by allowing it to access an entire training set of parallel sentence pairs even after training shows that the proposed approach significantly outperforms the baseline approach and the improvement is more significant when more relevant sentence pairs were retrieved.
View PDF on arXiv (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)