Mirroring Vector Space Embedding for New Words
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Jihye | - |
dc.contributor.author | Jeong, Ok-Ran | - |
dc.date.accessioned | 2021-08-05T01:40:26Z | - |
dc.date.available | 2021-08-05T01:40:26Z | - |
dc.date.created | 2021-08-02 | - |
dc.date.issued | 2021-07 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/81821 | - |
dc.description.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 | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.relation.isPartOf | IEEE Access | - |
dc.title | Mirroring Vector Space Embedding for New Words | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.description.journalClass | 1 | - |
dc.identifier.wosid | 000675197100001 | - |
dc.identifier.doi | 10.1109/ACCESS.2021.3096238 | - |
dc.identifier.bibliographicCitation | IEEE Access, v.9, pp.99954 - 99967 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85110831872 | - |
dc.citation.endPage | 99967 | - |
dc.citation.startPage | 99954 | - |
dc.citation.title | IEEE Access | - |
dc.citation.volume | 9 | - |
dc.contributor.affiliatedAuthor | Kim, Jihye | - |
dc.contributor.affiliatedAuthor | Jeong, Ok-Ran | - |
dc.type.docType | Article in Press | - |
dc.subject.keywordAuthor | Artificial Intelligence | - |
dc.subject.keywordAuthor | Bit error rate | - |
dc.subject.keywordAuthor | Data models | - |
dc.subject.keywordAuthor | Deep Learning | - |
dc.subject.keywordAuthor | Dictionaries | - |
dc.subject.keywordAuthor | Hidden Markov models | - |
dc.subject.keywordAuthor | Natural Language Processing | - |
dc.subject.keywordAuthor | Neural Networks | - |
dc.subject.keywordAuthor | New Words | - |
dc.subject.keywordAuthor | Semantics | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Word Embedding | - |
dc.subject.keywordPlus | Convolutional neural networks | - |
dc.subject.keywordPlus | Embeddings | - |
dc.subject.keywordPlus | Learning systems | - |
dc.subject.keywordPlus | Natural language processing systems | - |
dc.subject.keywordPlus | Reusability | - |
dc.subject.keywordPlus | External resources | - |
dc.subject.keywordPlus | NAtural language processing | - |
dc.subject.keywordPlus | Novel strategies | - |
dc.subject.keywordPlus | Vector-space embedding | - |
dc.subject.keywordPlus | Vector spaces | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
1342, Seongnam-daero, Sujeong-gu, Seongnam-si, Gyeonggi-do, Republic of Korea(13120)031-750-5114
COPYRIGHT 2020 Gachon University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.