Unsupervised Spectral Learning of Finite State Transducers thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Unsupervised Spectral Learning of Finite State Transducers

Published on Nov 07, 20141777 Views

Finite-State Transducers (FST) are a standard tool for modeling paired input-output sequences and are used in numerous applications, ranging from computational biology to natural language processing.

Related categories

Chapter list

Unsupervised Learning of Finite State Transducers02:25
Spectral Method02:30
Unsupervised Spectral Method02:41
Solving the rank minimization problem03:27