Knowledge base completion with translation based embeddings and negative sampling method = 지식 베이스 완성을 위한 트랜슬레이션 기반 임베딩 및 거짓 지식 샘플링 방법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 217
  • Download : 0
How to complete knowledge is one of the most important issue of knowledge bases, because of their large size and sparsity. To complete the knowledge bases, we need a model that can predict undefined relationships between entities. TransE has been a promising method to complete knowledge bases by using a translation concept, and improved approaches has been proposed based on TransE. However, these models common issue that they do not actually represent translation, and it causes lower performances. Here we propose a new embedding method, TTE which makes the translation concept better use. TTE uses a new objective function, which can learn translation relationships between entities and relations. TTE outperforms previous translation based approaches in a link prediction task on two knowledge bases without increasing the number of parameters. Another characteristic of knowledge bases is that they do not contain false samples. Traditional approaches of negative sampling regard randomly sampled knowledge as false. However, randomly sampled knowledge can contain true knowledge, which does not belong to dataset, and these knowledge lower the performances. In this thesis, we propose a new way to do negative sampling by using pretrained word embeddings.
Advisors
Lee, Soo-Youngresearcher이수영researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2018
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2018.2,[ii, 27 p. :]

Keywords

Knowledge base▼aEmbedding▼aTranslation▼aNegative sampling; 지식 베이스▼a임베딩▼a트랜슬레이션▼a거짓 지식 샘플링

URI
http://hdl.handle.net/10203/266890
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=733991&flag=dissertation
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0