[1]胡万亭,郭建英,张继永.一种基于改进 ELMO 模型的组织机构名识别方法[J].计算机技术与发展,2020,30(11):25-29.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 005]
　HU Wan-ting,GUO Jian-ying,ZHANG Ji-yong.An Organization Name Recognition Method Based on Improved ELMO Model[J].,2020,30(11):25-29.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 005]
点击复制

一种基于改进 ELMO 模型的组织机构名识别方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年11期
页码:
25-29
栏目:
智能、算法、系统工程
出版日期:
2020-11-10

文章信息/Info

Title:
An Organization Name Recognition Method Based on Improved ELMO Model
文章编号:
1673-629X(2020)11-0025-05
作者:
胡万亭1; 郭建英1; 张继永2
1. 河南大学 濮阳工学院,河南 濮阳 457000;2. 西南交通大学 信息科学与技术学院,四川 成都 610000
Author(s):
HU Wan-ting1; GUO Jian-ying1; ZHANG Ji-yong2
1. Puyang Institute of Technology,Henan University,Puyang 457000,China; 2. School of Information Science and Technology,Southwest Jiaotong University,Chengdu 610000,China
关键词:
ELMO 模型; LSTM 模型; 机构词; 条件随机场; 组织机构名识别
Keywords:
ELMO model; LSTM model; organization word; conditional random field; organization name recognition
分类号:
TP301. 6
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 11. 005
摘要:
组织机构名识别是命名实体识别的核心任务之一,也是最困难的任务。 近年来,预训练模型在中文自然语言处理领域得到广泛应用, 预训练的词嵌入模型在中文命名实体识别上取得了非常好的效果,但是在组织机构名识别上还有很大的提升空间。 针对这一问题,改进 ELMO(embedding from language models)预训练模型,结合双向 LSTM 神经网络模型和条件随机场模型,去识别组织机构名。 对于 ELMO 的改进,主要通过筛选高频机构词,然后将高频机构词加入中文字典,通过 ELMO 模型训练生成机构词向量和普通字向量。 字向量不用考虑未登录词的问题,机构词向量引入了先验知识,结合起来可以使得生成的字词向量能够更好地表征组织机构名。 实验结果表明,预训练模型的数据集相对较小时,该方法比字向量嵌入的方法有更好的效果,F1 值提高了 1.3% 。
Abstract:
Organization name recognition is one of the primary tasks of named entity recognition and the most difficult task. Recently,the pre-training model has been widely used in the field of Chinese natural language processing. The word embedding model has achieved excellent results in Chinese named entity recognition,but there is still much room for improvement in organization name recognition. To solve the problem,the ELMO (embedding from language models) is improved,and then it is combined with the Bi-LSTM model and conditional random field model to identify the organization name. The improvement of ELMO is mainly through filtering high-frequency organization words,then adding them into Chinese character set,and generating organization word vector and character vector through ELMO model training. The character vector hasn’ t the problem of unknown words and organization word vector introduces prior knowledge,which can be combined to make the generated word vector can better represent the organization name. The experiment shows that when the data set of the pre-training model is relatively small, the proposed method has a better effect than the word vector embedding method,with F1 value increasing by 1.3% .

相似文献/References:

[1]范禹辰,刘相坤,朱建生,等.基于 BERT 的服务网站 Web 攻击检测研究[J].计算机技术与发展,2022,32(08):168.[doi:10. 3969 / j. issn. 1673-629X. 2022. 08. 027]
　FAN Yu-chen,LIU Xiang-kun,ZHU Jian-sheng,et al.Research on Web Attack Detection of Service Website Based on BERT[J].,2022,32(11):168.[doi:10. 3969 / j. issn. 1673-629X. 2022. 08. 027]
[2]庞梦吟,王海宁,万通明,等.基于组合预测模型的疫情确诊人数预测[J].计算机技术与发展,2022,32(11):198.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 029]
　PANG Meng-yin,WANG Hai-ning,WAN Tong-ming,et al.Epidemic Data Prediction Based on Combined Prediction Model[J].,2022,32(11):198.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 029]

更新日期/Last Update: 2020-11-10