SemSeq: A Regime for Training Widely-Applicable Word-Sequence Encoders.

Hiroaki Tsuyuki Tetsuji Ogawa Tetsunori Kobayashi Yoshihiko Hayashi

Published in: PACLING (2019)

Keyphrases

widely applicable
learning theory
training algorithm
training set
training examples
n gram
data sets
neural network
co occurrence
training phase
machine learning
learning algorithm
knowledge base
semi supervised