Natural Language Processing
 
Edit

Machine Translation

2143 papers with code • 78 benchmarks • 76 datasets

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

Approaches for machine translation can range from rule-based to statistical to neural-based. More recently, encoder-decoder attention-based architectures like BERT have attained major improvements in machine translation.

One of the most popular datasets used to benchmark machine translation systems is the WMT family of datasets. Some of the most commonly used evaluation metrics for machine translation systems include BLEU, METEOR, NIST, and others.

( Image credit: Google seq2seq )

Libraries

Use these libraries to find Machine Translation models and implementations
awslabs/sockeye
24 papers
1,206
pytorch/fairseq
15 papers
29,174
huggingface/transformers
14 papers
124,353
tensorflow/tensor2tensor
10 papers
14,859
See all 13 libraries.

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

Style Transfer from Non-Parallel Text by Cross-Alignment

shentianxiao/language-style-transfer • • NeurIPS 2017

We demonstrate the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order.

12
Paper
Code

Self-Attention with Relative Position Representations

tensorflow/tensor2tensor • • NAACL 2018

On the WMT 2014 English-to-German and English-to-French translation tasks, this approach yields improvements of 1. 3 BLEU and 0. 3 BLEU over absolute position representations, respectively.

12
Paper
Code

Neural Machine Translation in Linear Time

paarthneekhara/byteNet-tensorflow • • 31 Oct 2016

The ByteNet is a one-dimensional convolutional neural network that is composed of two parts, one to encode the source sequence and the other to decode the target sequence.

11
Paper
Code

Simple Recurrent Units for Highly Parallelizable Recurrence

asappresearch/sru • • EMNLP 2018

Common recurrent neural architectures scale poorly due to the intrinsic difficulty in parallelizing their state computations.

11
Paper
Code

XNLI: Evaluating Cross-lingual Sentence Representations

facebookresearch/XLM • • EMNLP 2018

State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models.

10
Paper
Code

Population Based Training of Neural Networks

MattKleinsmith/pbt • • 27 Nov 2017

Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm.

9
Paper
Code

OpenNMT: Neural Machine Translation Toolkit

rsennrich/nematus • • WS 2018

OpenNMT is an open-source toolkit for neural machine translation (NMT).

9
Paper
Code

Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings

facebookresearch/LASER • • ACL 2019

Machine translation is highly sensitive to the size and quality of the training data, which has led to an increasing interest in collecting and filtering large parallel corpora.

9
Paper
Code

Unsupervised Translation of Programming Languages

facebookresearch/CodeGen • NeurIPS 2020

We train our model on source code from open source GitHub projects, and show that it can translate functions between C++, Java, and Python with high accuracy.

9
Paper
Code

Linear Transformers Are Secretly Fast Weight Programmers

ischlag/fast-weight-transformers • • 22 Feb 2021

We show the formal equivalence of linearised self-attention mechanisms and fast weight controllers from the early '90s, where a ``slow" neural net learns by gradient descent to program the ``fast weights" of another net through sequences of elementary programming instructions which are additive outer products of self-invented activation patterns (today called keys and values).

9
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy