DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김석환 | en_US |
dc.date.accessioned | 2014-12-01T11:47:42Z | - |
dc.date.available | 2014-12-01T11:47:42Z | - |
dc.date.issued | 2012 | en_US |
dc.identifier.other | OAK-2014-00825 | en_US |
dc.identifier.uri | http://postech.dcollection.net/jsp/common/DcLoOrgPer.jsp?sItemId=000001215404 | en_US |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/1327 | - |
dc.description | Doctor | en_US |
dc.description.abstract | Relation extraction is the task of identifying semantic relationships between named entities in natural language documents. Many researchers have conducted extensive studies on relation extraction in the last decade | en_US |
dc.description.abstract | however, statistical systems based on supervised learning are still limited because they require large amounts of training data to achieve a high performance level.This dissertation proposes cross-lingual annotation projection approaches for relation extraction. The main idea of this approach is to obtain training examples in a resource-poor language without significant annotation efforts by utilizing parallel corpora. The annotations in the resource-rich source language sentences are propagated to the corresponding target language sentences through the results of word alignment.To make our method more reliable, we introduce two projection approaches: direct projection and graph-based projection. Direct projection is presented with noise reduction strategies to improve robustness against errors generated by preprocessing. The graph-based projection approach adopts a label propagation algorithm to generate quality projections. We demonstrate the merit of our methods using a Korean relation extraction system trained on projected examples from an English-Korean parallel corpus. Experiments show the feasibility of our approach through a comparison to other systems based on monolingual resources. | en_US |
dc.language | eng | en_US |
dc.publisher | 포항공과대학교 | en_US |
dc.rights | BY_NC_ND | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/2.0/kr | en_US |
dc.title | 의미 관계의 교차 언어 반교사 학습 | en_US |
dc.title.alternative | Cross-Lingual Weakly-Supervised Learning of Semantic Relations | en_US |
dc.type | Thesis | en_US |
dc.contributor.college | 일반대학원 컴퓨터공학과 | en_US |
dc.date.degree | 2012- 2 | en_US |
dc.type.docType | Thesis | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.