DC Field | Value | Language |
---|---|---|
dc.contributor.author | 정예원 | - |
dc.date.accessioned | 2022-03-29T03:36:08Z | - |
dc.date.available | 2022-03-29T03:36:08Z | - |
dc.date.issued | 2020 | - |
dc.identifier.other | OAK-2015-09071 | - |
dc.identifier.uri | http://postech.dcollection.net/common/orgView/200000287250 | ko_KR |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/111876 | - |
dc.description | Master | - |
dc.description.abstract | We propose a Korean named entity recognition (NER) model which extracts affix features to augment word representations. We build upon two recently prominently used NER models, namely BiLSTM-BiLSTM-CRF and CNN-BiLSTM-CRF, by extending the word embeddings with approximated affix information. We choose to use an inexpensive character-level frequency filter to infer the affix information. Our experimental results on the HCLT 2016 and ETRI NER datasets show up to a 0.93% increase in F1 score compared to the original models without any dictionary or morphological tools. This increase is a significant improvement in NER considering the recent stagnation following the introduction of neural NER. These results show that Korean predicted affix features are useful in building neural NER models. | - |
dc.language | kor | - |
dc.publisher | 포항공과대학교 | - |
dc.title | Extending Word Representations with Affix Features for Bidirectional LSTM-CRF-based Korean Named Entity recognition | - |
dc.title.alternative | Bidirectional LSTM-CRF 기반의 한국어 개체명 인식을 위한 접사 자질을 이용한 단어 표상 확장 | - |
dc.type | Thesis | - |
dc.contributor.college | 일반대학원 컴퓨터공학과 | - |
dc.date.degree | 2020- 2 | - |
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.