earticle

논문검색

Uyghur Stemming and Lemmatization Approach based on Multi-Morphological Features

초록

영어

This paper describes a stemming and lemmatization approach for Uyghur using Conditional Random Fields (CRFs). In the proposed approach, we used syllable-level training and test corpus with the combination of some automatically tagged positional and morphological feature tags. The training and test corpus has been manually tagged with a stemming tag set which includes eight kinds of tags which fully reflect the morphological feature of Uyghur word. It has been observed that some morphological features are very helpful for improving the evaluating results. The syllable-level Precision, Recall and F-score of the best evaluation result respectively are 98.79%,98.71% and 98.75% respectively, and the word-level accuracy we achieved is 95.9%.The experimental results show that the efficiency of this approach is very ideal.

목차

Abstract
 1. Introduction
 2. Syllable-Level Tagging Approach
 3. Data Preparation
  3.1. Syllable Corpus
  3.2. Auto-Tagged Corpus
  3.3. CRFs Corpus
 4. Feature Templates and Training
 5. Testing and Evaluating
  5.1. Testing
  5.2. Syllable-Level Evaluating
 6. Post-Processing and Word-Level Evaluating
 7. Conclusion and Future Work
 References

저자정보

  • Abdurahim Mahmoud Institute of Information Science and Engineering, Xinjiang University, China
  • Sediyegvl Enwer Institute of Information Science and Engineering, Xinjiang University, China
  • Abdusalam Dawut School of Software, Xinjiang University, Urumqi, China
  • Palidan Tuerxun School of Software, Xinjiang University, Urumqi, China
  • Askar Hamdulla Institute of Information Science and Engineering, Xinjiang University, China

참고문헌

    ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

    0개의 논문이 장바구니에 담겼습니다.