Mirroring Vector Space Embedding for New Words

Mirroring Vector Space Embedding for New Words

Most embedding models used in natural language processing require retraining of the entire model to obtain the embedding value of a new word. In the current system, as retraining is repeated, the amount of data used for learning gradually increases. It is thus very inefficient to retrain the entire...

Full description

Bibliographic Details
Main Authors: Jihye Kim, Ok-Ran Jeong
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Artificial intelligence
deep learning
natural language processing
neural networks
new words
word embedding
Online Access:https://ieeexplore.ieee.org/document/9481109/

Internet

https://ieeexplore.ieee.org/document/9481109/

Similar Items