Browse > Natural Language Processing > Machine Translation

Machine Translation

365 papers with code · Natural Language Processing

Machine translation is the task of translating a sentence in a source language to a different target language.

State-of-the-art leaderboards

Trend Dataset Best Method Paper title Paper Code Compare

Latest papers without code

Multilingual Neural Machine Translation with Knowledge Distillation

ICLR 2019 Xu Tan et al

Multilingual machine translation, which translates multiple languages with a single model, has attracted much attention due to its efficiency of offline training and online serving.

MACHINE TRANSLATION

01 May 2019

Hyperbolic Attention Networks

ICLR 2019 Caglar Gulcehre et al

Recent approaches have successfully demonstrated the benefits of learning the parameters of shallow networks in hyperbolic space.

MACHINE TRANSLATION QUESTION ANSWERING VISUAL QUESTION ANSWERING

01 May 2019

Minimum Divergence vs. Maximum Margin: an Empirical Comparison on Seq2Seq Models

ICLR 2019 Huan Zhang et al

Sequence to sequence (seq2seq) models have become a popular framework for neural sequence prediction.

MACHINE TRANSLATION

01 May 2019

Area Attention

ICLR 2019 Yang Li et al

Existing attention mechanisms, are mostly item-based in that a model is trained to attend to individual items in a collection (the memory) where each item has a predefined, fixed granularity, e. g., a character or a word.

IMAGE CAPTIONING MACHINE TRANSLATION

01 May 2019

Improving Sequence-to-Sequence Learning via Optimal Transport

ICLR 2019 Liqun Chen et al

Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE).

ABSTRACTIVE TEXT SUMMARIZATION IMAGE CAPTIONING MACHINE TRANSLATION

01 May 2019

Graph Convolutional Network with Sequential Attention For Goal-Oriented Dialogue Systems

ICLR 2019 Suman Banerjee et al

Domain specific goal-oriented dialogue systems typically require modeling three types of inputs, viz., (i) the knowledge-base associated with the domain, (ii) the history of the conversation, which is a sequence of utterances and (iii) the current utterance for which the response needs to be generated.

GOAL-ORIENTED DIALOGUE SYSTEMS MACHINE TRANSLATION SEMANTIC ROLE LABELING

01 May 2019

Hint-based Training for Non-Autoregressive Translation

ICLR 2019 Zhuohan Li et al

To improve the accuracy of NART models, in this paper, we propose to leverage the hints from a well-trained ART model to train the NART model.

MACHINE TRANSLATION

01 May 2019

Towards a better understanding of Vector Quantized Autoencoders

ICLR 2019 Aurko Roy et al

Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks.

MACHINE TRANSLATION

01 May 2019

Diverse Machine Translation with a Single Multinomial Latent Variable

ICLR 2019 Tianxiao Shen et al

There are many ways to translate a sentence into another language.

MACHINE TRANSLATION

01 May 2019

On Meaning-Preserving Adversarial Perturbations for Sequence-to-Sequence Models

ICLR 2019 Paul Michel et al

Adversarial examples have been shown to be an effective way of assessing the robustness of neural sequence-to-sequence (seq2seq) models, by applying perturbations to the input of a model leading to large degradation in performance.

MACHINE TRANSLATION

01 May 2019