基于特征相似度的可比语料挖掘汉柬命名实体等价对!.pdfVIP

Vol.45 No. 5 璁＄畻鏈轰笌鏁板瓧宸ョ▼ 鎬荤331 鏈 882 Computer Digital Engineering 绗?5 鍗 2017 骞寸5 鏈 鍩轰簬鐗瑰緛鐩镐技搴︾殑鍙瘮璇枡鎸栨帢姹夋煬鍛藉悕瀹炰綋绛変环瀵光垪 1锛? 1锛? 1锛? 1锛? 3 寰 鐠 涓 棣 澶 闈 鍛 鏋 鑾簮婧 锛?. 鏄嗘槑鐞嗗伐澶у淇℃伅宸ョ▼涓庤嚜鍔ㄥ寲瀛﹂櫌 鏄嗘槑 650500锛夛紙2. 鏄嗘槑鐞嗗伐澶у鏅鸿兘淇℃伅澶勭悊閲嶇偣瀹為獙瀹 鏄嗘槑 650500锛 锛?. 浜戝崡姘戞棌澶у涓滃崡浜氬崡浜氳瑷€鏂囧寲瀛﹂櫌 鏄嗘槑 650500锛 鎽 瑕 鍛藉悕瀹炰綋缈昏瘧绛変环瀵瑰湪璺ㄨ瑷€淇℃伅澶勭悊涓叿鏈夐潪甯搁噸瑕佺殑搴旂敤浠峰€硷紝鐒惰€岀敱浜庤鏂欒祫婧愮殑鏈夐檺鎬э紝鍥藉唴澶栧叧 浜庢眽鏌懡鍚嶅疄浣撶瓑浠峰鐨勬娊鍙栨柟娉曡繕娌℃湁娣卞叆鐮旂┒銆傝鏂囦粠鍙瘮璇枡鏂囨湰鍑哄彂锛屾牴鎹笉鍚岀被鍨嬪疄浣撹绱犵殑鐗圭偣浠ュ強鍦ㄥ彲姣 璇枡涓殑鐗圭偣锛岄€夊彇浜嗘煬鏂囧懡鍚嶅疄浣撳埌涓枃鍛藉悕瀹炰綋鐨勯煶璇戠壒寰併€佺炕璇戠壒寰併€佸彲姣旇鏂欎腑鍛藉悕瀹炰綋鐨勪笂涓嬫枃鐗瑰緛鍙婅嚜韬殑闀 搴︾壒寰侊紝鎻愬嚭浜嗕竴绉嶅熀浜庡鐗瑰緛铻嶅悎鏉ヨ绠楃浉浼煎害鐨勬柟娉曟潵鎸栨帢姹夋煬鍙岃鍛藉悕瀹炰綋绛変环瀵广€傚疄楠岃〃鏄庤鏂规硶鍙栧緱浜嗘瘮杈冨ソ 鐨勬晥鏋滐紝鍏朵腑鎸栨帢浜哄悕瀹炰綋瀵圭殑鍑嗙‘鐜囪揪鍒?6%锛屽彫鍥炵巼杈惧埌66%锛岃瘉鏄庝簡璇ユ柟娉曡浼樹簬鍙噰鐢ㄥ崟涓€鐗瑰緛鐨勬柟娉曘€ 鍏抽敭璇 鍛藉悕瀹炰綋绛変环瀵癸紱姹夋煬鍙岃锛涘鐗瑰緛铻嶅悎锛涘彲姣旇鏂欙紱闊宠瘧妯″瀷 涓浘鍒嗙被鍙 TP391.1 DOI锛?0. 3969/j. issn. 1672-9722. 2017. 05. 020 Chinese-KhmerNamedEntityEquivalentsExcavationBasedon FeatureSimilarityinComparableCorpus 1锛? 1锛? 1锛? 1锛? 3 XULu YANXin XIAQing ZHOUFeng MOYuanyuan 锛?. School of Information Engineering and Automation锛孠unming University of Science and Technology锛孠unming 650500锛 锛?. The Intelligent Information Processing Key Laboratory锛孠unming University of Science and Technology锛孠unming 650500锛 锛?. School of Southeast Asia South Asia Languages and Cultures锛孻unnan Minzu University锛孠unming 650500锛 Abstract Named entity translation equivalent has been playing a significant role in the processing of cross-language informa鈦 tion. However limited by the corpora resource 锛宖ew in-depth studies have