Browse > Natural Language Processing > Machine Translation

Machine Translation

484 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 with code

4
12 Oct 2019

Multilingual Question Answering from Formatted Text applied to Conversational Agents

10 Oct 2019wissam-sib/multilingualQA

Fortunately, state-of-the-art models are now being pre-trained on multiple languages (e. g. BERT was released in a multilingual version managing a hundred languages) and are exhibiting ability for zero-shot transfer from English to others languages on XNLI.

MACHINE TRANSLATION QUESTION ANSWERING READING COMPREHENSION

0
10 Oct 2019

On Dimensional Linguistic Properties of the Word Embedding Space

5 Oct 2019vyraun/Half-Size

In this work, we analyze word embeddings in terms of their principal components and arrive at a number of novel conclusions.

MACHINE TRANSLATION SENTENCE CLASSIFICATION WORD EMBEDDINGS

48
05 Oct 2019

Cross-Lingual Natural Language Generation via Pre-Training

23 Sep 2019CZWin32768/xnlg

After the pre-training procedure, we use monolingual data to fine-tune the pre-trained model on downstream NLG tasks.

ABSTRACTIVE TEXT SUMMARIZATION CROSS-LINGUAL TRANSFER MACHINE TRANSLATION QUESTION GENERATION TEXT GENERATION

6
23 Sep 2019

Creative GANs for generating poems, lyrics, and metaphors

20 Sep 2019Machine-Learning-Tokyo/Poetry-GAN

Generative models for text have substantially contributed to tasks like machine translation and language modeling, using maximum likelihood optimization (MLE).

LANGUAGE MODELLING MACHINE TRANSLATION TEXT GENERATION

8
20 Sep 2019

Espresso: A Fast End-to-end Neural Speech Recognition Toolkit

18 Sep 2019freewym/espresso

We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq.

DATA AUGMENTATION LANGUAGE MODELLING MACHINE TRANSLATION SPEECH RECOGNITION

490
18 Sep 2019

Hint-Based Training for Non-Autoregressive Machine Translation

15 Sep 2019zhuohan123/hint-nart

Due to the unparallelizable nature of the autoregressive factorization, AutoRegressive Translation (ART) models have to generate tokens sequentially during decoding and thus suffer from high inference latency.

MACHINE TRANSLATION

4
15 Sep 2019

Beyond BLEU: Training Neural Machine Translation with Semantic Similarity

14 Sep 2019jwieting/beyond-bleu

While most neural machine translation (NMT) systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can substantially improve final translation accuracy.

MACHINE TRANSLATION SEMANTIC TEXTUAL SIMILARITY

17
14 Sep 2019

Ouroboros: On Accelerating Training of Transformer-Based Language Models

14 Sep 2019LaraQianYang/Ouroboros

Model parallelism is required if a model is too large to fit in a single computing device.

LANGUAGE MODELLING MACHINE TRANSLATION TEXT SUMMARIZATION

8
14 Sep 2019