Attention Is All You Need

NeurIPS 2017 PaddlePaddle/models

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.

CONSTITUENCY PARSING MACHINE TRANSLATION

Bag of Tricks for Image Classification with Convolutional Neural Networks

CVPR 2019 PaddlePaddle/models

Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods.

IMAGE CLASSIFICATION OBJECT DETECTION SEMANTIC SEGMENTATION TRANSFER LEARNING

Pointer Networks

NeurIPS 2015 PaddlePaddle/models

It differs from the previous attention attempts in that, instead of using attention to blend hidden units of an encoder to a context vector at each decoder step, it uses attention as a pointer to select a member of the input sequence as the output.

COMBINATORIAL OPTIMIZATION

DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications

WS 2018 PaddlePaddle/models

Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements.

MACHINE READING COMPREHENSION

Proactive Human-Machine Conversation with Explicit Conversation Goals

13 Jun 2019PaddlePaddle/models

DuConv enables a very challenging task as the model needs to both understand dialogue and plan over the given knowledge graph.

Proactive Human-Machine Conversation with Explicit Conversation Goal

ACL 2019 PaddlePaddle/models

Konv enables a very challenging task as the model needs to both understand dialogue and plan over the given knowledge graph.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

8 Dec 2015PaddlePaddle/models

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages.

 SOTA for Speech Recognition on WSJ eval93 (using extra training data)

ACCENTED SPEECH RECOGNITION END-TO-END SPEECH RECOGNITION NOISY SPEECH RECOGNITION

Cannot find the paper you are looking for? You can Submit a new open access paper.