Mirroring Vector Space Embedding for New Words
- Authors
- Kim, Jihye; Jeong, Ok-Ran
- Issue Date
- Jul-2021
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Artificial Intelligence; Bit error rate; Data models; Deep Learning; Dictionaries; Hidden Markov models; Natural Language Processing; Neural Networks; New Words; Semantics; Task analysis; Training; Word Embedding
- Citation
- IEEE Access, v.9, pp.99954 - 99967
- Journal Title
- IEEE Access
- Volume
- 9
- Start Page
- 99954
- End Page
- 99967
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/81821
- DOI
- 10.1109/ACCESS.2021.3096238
- ISSN
- 2169-3536
- Abstract
- 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 model whenever some new words emerge. Moreover, since a language has a huge number of words and its characteristics change continuously over time, it is not easy to embed all words. To solve both problems, we propose a new embedding model, the Mirroring Vector Space (MVS), which enables us to obtain a new word embedding by using the previously built word embedding model without retraining it. The MVS embedding model has a convolutional neural networks (CNN) structure and presents a novel strategy to obtain word embeddings. It predicts the embedding value of a word by learning the vector space of an existing embedding model using the explanations of the word. It also provides flexibility for external resources, reusability for training times, and portability in the point that our model can be used with any models. We verify these three attributes and the novelty in our experiments. CCBYNCND
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 소프트웨어학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/81821)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.