Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Deep Learning for Joint Source-Channel Coding of Text

Abstract: 

We consider the problem of joint source and channel coding of structured data such as natural language over a noisy channel. The typical approach inspired by information theory to this problem involves performing source coding to first compress the text and then channel coding to add robustness while transmitting across the channel; this approach is optimal with arbitrarily large block lengths for discrete memoryless channels. Given documents of finite length and limitations on the length of the encoding, we achieve lower word error rates by developing a deep learning based encoder and decoder. While the information theoretic approach would minimize bit error rates, our approach preserves semantic information of sentences by first embedding sentences in a semantic space where sentences closer in meaning are located closer together, and then performing joint source and channel coding on these embeddings.

up
0 users have voted:

Paper Details

Authors:
Nariman Farsad, Milind Rao, and Andrea Goldsmith
Submitted On:
13 April 2018 - 11:22am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Milind Rao
Paper Code:
3599
Document Year:
2018
Cite

Document Files

icassp_jointSC_handout.pdf

(19 downloads)

Subscribe

[1] Nariman Farsad, Milind Rao, and Andrea Goldsmith, "Deep Learning for Joint Source-Channel Coding of Text", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2717. Accessed: May. 21, 2018.
@article{2717-18,
url = {http://sigport.org/2717},
author = {Nariman Farsad; Milind Rao; and Andrea Goldsmith },
publisher = {IEEE SigPort},
title = {Deep Learning for Joint Source-Channel Coding of Text},
year = {2018} }
TY - EJOUR
T1 - Deep Learning for Joint Source-Channel Coding of Text
AU - Nariman Farsad; Milind Rao; and Andrea Goldsmith
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2717
ER -
Nariman Farsad, Milind Rao, and Andrea Goldsmith. (2018). Deep Learning for Joint Source-Channel Coding of Text. IEEE SigPort. http://sigport.org/2717
Nariman Farsad, Milind Rao, and Andrea Goldsmith, 2018. Deep Learning for Joint Source-Channel Coding of Text. Available at: http://sigport.org/2717.
Nariman Farsad, Milind Rao, and Andrea Goldsmith. (2018). "Deep Learning for Joint Source-Channel Coding of Text." Web.
1. Nariman Farsad, Milind Rao, and Andrea Goldsmith. Deep Learning for Joint Source-Channel Coding of Text [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2717