earticle

논문검색

Named Entity Recognition using Word Embedding as a Feature

초록

영어

This study applied word embedding to feature for named entity recognition (NER) training, and used CRF as a learning algorithm. Named entities are phrases that contain the names of persons, organizations and locations and recognizing these entities in text is one of the important task of information extraction. Word embedding is helpful in many learning algorithms of NLP, indicating that words in a sentence are mapped by a real vector in a low-dimension space. We used GloVe, Word2Vec, and CCA as the embedding methods. The Reuters Corpus Volume 1 was used to create word embedding and the 2003 shared task corpus (English) of CoNLL was used for training and testing. As a result of comparing the performance of multiple techniques for word embedding to NER, it was found that CCA (85.96%) in Test A and Word2Vec (80.72%) in Test B exhibited the best performance. When using the word embedding as a feature of NER, it is possible to obtain better results than baseline that do not use word embedding. Also, to check that the word embedding well performed, we did additional experiment calculating the similarity between words.

목차

Abstract
 1. Introduction
 2. Named Entity Recognition
  2.1. Summary
  2.2. Data
 3. Word Embedding
  3.1. Global Vector
  3.2. Word2Vec
  3.3. Canonical Correlation Analysis (CCA)
 4. Feature Representation
  4.1. Baseline Features
  4.2. Word Embedding Features
 5. Conditional Random Field
 6. Experiments and Results
  6.1. Evaluation
  6.2. NER Results
  6.3. Nearest Neighbors of Word Embedding
 7. Conclusion
 References

저자정보

  • Miran Seok Department of Convergence Software, Hallym University, Korea, Bio-IT Research Center, Hallym University, Korea
  • Hye-Jeong Song Department of Convergence Software, Hallym University, Korea, Bio-IT Research Center, Hallym University, Korea
  • Chan-Young Park Department of Convergence Software, Hallym University, Korea, Bio-IT Research Center, Hallym University, Korea
  • Jong-Dae Kim Department of Convergence Software, Hallym University, Korea, Bio-IT Research Center, Hallym University, Korea
  • Yu-seop Kim Department of Convergence Software, Hallym University, Korea, Bio-IT Research Center, Hallym University, Korea

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

      0개의 논문이 장바구니에 담겼습니다.