Translating TED speeches by recurrent neural network based translation model
Lists
Only you see this
Abstract
This paper presents our recent progress on translating TED speeches <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> , a collection of public lectures covering a variety of topics. Specially, we use word-to-word alignment to compose translation units of bilingual tuples and present a recurrent neural network-based translation model (RNNTM) to capture long-span context during estimating translation probabilities of bilingual tuples. However, this RNNTM has severe data sparsity problem due to large tuple vocabulary and limited training data. Therefore, a factored RNNTM, which takes bilingual tuples in addition to source and target phrases of the tuples as input features, is proposed to partially address the problem. Our experimental results on the IWSLT2012 test sets show that the proposed models significantly improve the translation quality over state-of-the-art phrase-based translation systems.
BibTeX
@inproceedings{wu2014translating,
author = {Youzheng Wu and Xinhui Hu and Chiori Hori},
title = {{Translating TED speeches by recurrent neural network based translation model}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2014},
url = {https://openreview.net/forum?id=--UA-JIcV9J},
}Loading related content...