Marian: Fast Neural Machine Translation in C++

Autor: Ulrich Germann, Alham Fikri Aji, Marcin Junczys-Dowmunt, Tom Neckermann, Frank Seide, Kenneth Heafield, Tomasz Dwojak, Alexandra Birch, Roman Grundkiewicz, Nikolay Bogoychev, Hieu Hoang, André F. T. Martins

Publikováno v: arXiv.org e-Print Archive
Junczys-Dowmunt, M, Grundkiewicz, R, Dwojak, T, Hoang, H, Heafield, K, Neckermann, T, Seide, F, Germann, U, Aji, A F, Bogoychev, N, Martins, A F T & Birch, A 2018, Marian: Fast Neural Machine Translation in C++ . in Proceedings of ACL 2018, System Demonstrations . pp. 116–121, 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, 15/07/18 . https://doi.org/10.18653/v1/P18-4020
ACL (4)

We present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs. Marian is written entirely in C++. We describe the design of the encoder-

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b8a4e0feaecdc54c56b8d2572462ec31
http://arxiv.org/abs/1804.00344

The Deep Tensor Neural Network With Applications to Large Vocabulary Speech Recognition

Autor: Frank Seide, Dong Yu, Li Deng

Publikováno v: IEEE Transactions on Audio, Speech, and Language Processing. 21:388-396

The recently proposed context-dependent deep neural network hidden Markov models (CD-DNN-HMMs) have been proved highly promising for large vocabulary speech recognition. In this paper, we develop a more advanced type of DNN, which we call the deep te

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::cb8ee131eab5644540bbbe797564617a
https://doi.org/10.1109/tasl.2012.2227738

CNTK

Autor: Frank Seide, Amit Kumar Agarwal

Publikováno v: KDD

This tutorial will introduce the Computational Network Toolkit, or CNTK, Microsoft's cutting-edge open-source deep-learning toolkit for Windows and Linux. CNTK is a powerful computation-graph based deep-learning toolkit for training and evaluating de

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::eaabee02ed934e18d6896de2e1c6e448
https://doi.org/10.1145/2939672.2945397

Deep bi-directional recurrent networks over spectral windows

Autor: Gerald Penn, Dong Yu, Jasha Droppo, Geoffrey Zweig, Frank Seide, Andreas Stoicke, Abdelrahman Mohamed

Publikováno v: ASRU

Long short-term memory (LSTM) acoustic models have recently achieved state-of-the-art results on speech recognition tasks. As a type of recurrent neural network, LSTMs potentially have the ability to model long-span phenomena relating the spectral in

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9a0ae5f80f07d27d68b295957590c12c
https://doi.org/10.1109/asru.2015.7404777

The use of virtual hypothesis copies in decoding of large-vocabulary continuous speech

Autor: Frank Seide

Publikováno v: IEEE Transactions on Speech and Audio Processing. 13:520-533

High computational effort hinders wide-spread deployment of large-vocabulary continuous-speech recognition (LVCSR), for example in home or mobile devices. To this end, we developed a novel approach to LVCSR Viterbi decoding with significantly reduced

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::408fdeb8695eaa18ff8e12bdf96022b3
https://doi.org/10.1109/tsa.2005.848886