paper-with-me

Papers

RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition

2018-05-14 · ACL 2018 7 · Albert Zeyer, Tamer Alkhouli, Hermann Ney

We compare the fast training and decoding speed of RETURNN of attention models for translation, due to fast CUDA LSTM kernels, and a fast pure TensorFlow beam search decoder. We show that a layer-wise pretraining scheme for recurrent attention models gives over 1% BLEU improvement absolute and it allows to train deeper recurrent encoder networks. Promising preliminary results on max. expected BLEU training are presented. We are able to train state-of-the-art models for translation and end-to-end models for speech recognition and show results on WMT 2017 and Switchboard. The flexibility of RETURNN allows a fast research feedback loop to experiment with alternative architectures, and its generality allows to use it on a wide range of applications.

📄 PDF Abstract BibTeX arXiv:1805.05225

Code (3)

rwth-i6/returnn 공식 구현 tf
danenergetics/returnn tf
papar22/returnn-my-branch tf

Tasks

Decoderspeech-recognitionSpeech RecognitionTranslation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning

2018-07-09 · Álvaro Peris, Francisco Casacuberta

We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predicti…

General ClassificationMachine TranslationNMTQuestion Answering+6

NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems

2017-06-01 · Ozan Caglayan, Mercedes García-Martínez, Adrien Bardet, Walid Aransa 외

In this paper, we present nmtpy, a flexible Python toolkit based on Theano for training Neural Machine Translation and other neural sequence-to-sequence architectures. nmtpy decouples the specification of a network from …

Machine TranslationMultimodal Machine TranslationTranslation

Texar: A Modularized, Versatile, and Extensible Toolbox for Text Generation

2018-07-01 · WS 2018 7 · Zhiting Hu, Zichao Yang, Tiancheng Zhao, Haoran Shi 외

We introduce Texar, an open-source toolkit aiming to support the broad set of text generation tasks. Different from many existing toolkits that are specialized for specific applications (e.g., neural machine translation)…

Image CaptioningMachine TranslationText GenerationText Summarization+1

Flexible retrieval with NMSLIB and FlexNeuART

2020-10-28 · EMNLP (NLPOSS) 2020 11 · Leonid Boytsov, Eric Nyberg

Our objective is to introduce to the NLP community an existing k-NN search library NMSLIB, a new retrieval toolkit FlexNeuART, as well as their integration capabilities. NMSLIB, while being one the fastest k-NN search li…

Re-RankingRetrieval

RETURNN: The RWTH Extensible Training framework for Universal Recurrent Neural Networks

2016-08-02 · Patrick Doetsch, Albert Zeyer, Paul Voigtlaender, Ilya Kulikov 외

In this work we release our extensible and easily configurable neural network training software. It provides a rich set of functional layers with a particular focus on efficient training of recurrent neural network topol…