DeepAI AI Chat
Log In Sign Up

Latent Sequence Decompositions

10/10/2016
by   William Chan, et al.
Google
MIT
Carnegie Mellon University
0

We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorithm which samples valid extensions and an approximate decoding algorithm. We experiment with the Wall Street Journal speech recognition task. Our LSD model achieves 12.9 compared to a character baseline of 14.8 convolutional network on the encoder, we achieve 9.6

READ FULL TEXT
08/03/2016

Learning Online Alignments with Continuous Rewards Policy Gradient

Sequence-to-sequence models with soft attention had significant success ...
11/21/2015

Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification

Connectionist temporal classification (CTC) based supervised sequence tr...
03/22/2020

A Better Variant of Self-Critical Sequence Training

In this work, we present a simple yet better variant of Self-Critical Se...
12/28/2020

Enhancing Handwritten Text Recognition with N-gram sequence decomposition and Multitask Learning

Current state-of-the-art approaches in the field of Handwritten Text Rec...
09/26/2016

Online Segment to Segment Neural Transduction

We introduce an online neural sequence to sequence model that learns to ...
10/02/2018

Optimal Completion Distillation for Sequence Learning

We present Optimal Completion Distillation (OCD), a training procedure f...
08/03/2017

Sensor Transformation Attention Networks

Recent work on encoder-decoder models for sequence-to-sequence mapping h...