Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (2): 356-364.DOI: 10.11772/j.issn.1001-9081.2021122142
Special Issue: 人工智能
• Artificial intelligence • Previous Articles Next Articles
Qingtang LIU, Xinqian MA(), Jie ZHOU, Linjing WU, Pengxiao ZHOU
Received:
2021-11-24
Revised:
2022-06-28
Accepted:
2022-07-13
Online:
2022-08-03
Published:
2023-02-10
Contact:
Xinqian MA
About author:
LIU Qingtang, born in 1969, Ph. D., professor. His research interests include digital learning, copyright protection, knowledge mining, knowledge services.Supported by:
通讯作者:
马鑫倩
作者简介:
刘清堂(1969—),男,湖北仙桃人,教授,博士,主要研究方向:数字化学习、版权保护、知识挖掘、知识服务基金资助:
CLC Number:
Qingtang LIU, Xinqian MA, Jie ZHOU, Linjing WU, Pengxiao ZHOU. Understanding of math word problems integrating commonsense knowledge base and grammatical features[J]. Journal of Computer Applications, 2023, 43(2): 356-364.
刘清堂, 马鑫倩, 周洁, 吴林静, 周鹏霄. 融合常识库和语法特征的数学应用题题意理解[J]. 《计算机应用》唯一官方网站, 2023, 43(2): 356-364.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2021122142
类型 | 典型例题 | 题意理解关键参数 | 算式 | |||
---|---|---|---|---|---|---|
基本事件 | 实验事件 | 隐藏常识信息 | 求解 | |||
常规题目 | 一个暗箱里装有5个小球,其中红球3个,黄球2个,从中不放回地抽取2个,抽到2个红球的概率是() | 一个暗箱里装有5 个小球,其中红球 3个,黄球2个 | 从中不放回地 抽取两个 | — | 抽取2个 红球的 概率 | |
常识隐藏 题目 | 随机掷一枚均匀的骰子, 点数小于3的概率是() | 一枚均匀的骰子 | 随机掷一枚 | a.骰子有6个面,出现概率是1∶1∶1∶1∶1∶1 b.小于3的点数有1,2 | 点数小于 3的概率 |
Tab. 1 Typical examples of classical probability word problem
类型 | 典型例题 | 题意理解关键参数 | 算式 | |||
---|---|---|---|---|---|---|
基本事件 | 实验事件 | 隐藏常识信息 | 求解 | |||
常规题目 | 一个暗箱里装有5个小球,其中红球3个,黄球2个,从中不放回地抽取2个,抽到2个红球的概率是() | 一个暗箱里装有5 个小球,其中红球 3个,黄球2个 | 从中不放回地 抽取两个 | — | 抽取2个 红球的 概率 | |
常识隐藏 题目 | 随机掷一枚均匀的骰子, 点数小于3的概率是() | 一枚均匀的骰子 | 随机掷一枚 | a.骰子有6个面,出现概率是1∶1∶1∶1∶1∶1 b.小于3的点数有1,2 | 点数小于 3的概率 |
组成 | 关键参数 | 参数标签(缩写) | 实例 | |
---|---|---|---|---|
题目 | 参数值 | |||
基本事件描述 | 基本事物名称 | Entity_name(Nam) | 现有小球5个 | 小球 |
基本事物数量 | Entity_number(Num) | 5 | ||
基本事物属性名 | Information_name(Inf_nam) | 颜色各不相同 | 颜色 | |
基本事物属性值 | Entity_Information(Inf) | 其中红球3个,黄球2个 | 红球,黄球 | |
属性事物数量 | Information_number(Inf_num) | 3,2 | ||
实验事件描述 | 发生次数 | Quantity(Quan) | 从中不放回地抽取2次 | 2 |
发生方式 | Method(Meth) | 不放回 |
Tab. 2 Representation model of classical probability word problem
组成 | 关键参数 | 参数标签(缩写) | 实例 | |
---|---|---|---|---|
题目 | 参数值 | |||
基本事件描述 | 基本事物名称 | Entity_name(Nam) | 现有小球5个 | 小球 |
基本事物数量 | Entity_number(Num) | 5 | ||
基本事物属性名 | Information_name(Inf_nam) | 颜色各不相同 | 颜色 | |
基本事物属性值 | Entity_Information(Inf) | 其中红球3个,黄球2个 | 红球,黄球 | |
属性事物数量 | Information_number(Inf_num) | 3,2 | ||
实验事件描述 | 发生次数 | Quantity(Quan) | 从中不放回地抽取2次 | 2 |
发生方式 | Method(Meth) | 不放回 |
特征 | 缩写 | 特征说明 | 取值 |
---|---|---|---|
词法 特征 | W | 词特征 | 所有可能的词 |
P | 词性特征 | 所有可能的词性 | |
Q | 数量词特征 | 布尔型:Y,N | |
M | 专有名词特征 | 布尔型:Y,N | |
句法 特征 | D | 句法特征 | 核心词(HED)、主谓关系(SBV)、动宾关系(VOB)、并列关系(COO)、定中关系(ATT)、状中结构(ADV)等 |
边界 特征 | B | 边界特征 | B、M、E、S、O |
Tab. 3 Multi-dimensional grammatical features of classical probability word problem meaning parameter identification
特征 | 缩写 | 特征说明 | 取值 |
---|---|---|---|
词法 特征 | W | 词特征 | 所有可能的词 |
P | 词性特征 | 所有可能的词性 | |
Q | 数量词特征 | 布尔型:Y,N | |
M | 专有名词特征 | 布尔型:Y,N | |
句法 特征 | D | 句法特征 | 核心词(HED)、主谓关系(SBV)、动宾关系(VOB)、并列关系(COO)、定中关系(ATT)、状中结构(ADV)等 |
边界 特征 | B | 边界特征 | B、M、E、S、O |
窗口 大小 | 类型 | 形式化表示 |
---|---|---|
3 | 一元特征模板 | U1:%x[-1,0] |
U2:%x[0,0] | ||
U3:%x[1,0] | ||
二元特征模板 | U4:%[-1,0]/%x[0,0] | |
U5:%x[0,0]/%x[1,0] | ||
三元特征模板 | U6:%x[-1,0]/%x[0,0]/%x[1,0] | |
5 | 一元特征模板 | U1:%x[-2,0] |
U2:%x[-1,0] | ||
U3:%x[0,0] | ||
U4:%x[1,0] | ||
U5:%x[2,0] | ||
二元特征模板 | U6:%x[-2,0]/%x[-1,0] | |
U7:%x[-1,0]/%x[0,0] | ||
U8:%x[0,0]/%x[1,0] | ||
U9:%x[1,0]/%x[2,0] | ||
三元特征模板 | U10:%x[-2,0]/%x[-1,0]/%x[0,0] | |
U11:%x[-1,0]/%x[0,0]/%x[1,0] | ||
U12:%x[0,0]/%x[1,0]/%x[2,0] | ||
四元特征模板 | U13:%x[-2,0]/%x[-1,0]/%x[0,0]/%x[1,0] | |
U14:%x[-1,0]/%x[0,0]/%x[1,0]/%x[2,0] | ||
五元特征模板 | U15:%x[-2,0]/%x[-1,0]/%x[0,0]/%x[1,0]/%x[2,0] |
Tab. 4 Design of feature template
窗口 大小 | 类型 | 形式化表示 |
---|---|---|
3 | 一元特征模板 | U1:%x[-1,0] |
U2:%x[0,0] | ||
U3:%x[1,0] | ||
二元特征模板 | U4:%[-1,0]/%x[0,0] | |
U5:%x[0,0]/%x[1,0] | ||
三元特征模板 | U6:%x[-1,0]/%x[0,0]/%x[1,0] | |
5 | 一元特征模板 | U1:%x[-2,0] |
U2:%x[-1,0] | ||
U3:%x[0,0] | ||
U4:%x[1,0] | ||
U5:%x[2,0] | ||
二元特征模板 | U6:%x[-2,0]/%x[-1,0] | |
U7:%x[-1,0]/%x[0,0] | ||
U8:%x[0,0]/%x[1,0] | ||
U9:%x[1,0]/%x[2,0] | ||
三元特征模板 | U10:%x[-2,0]/%x[-1,0]/%x[0,0] | |
U11:%x[-1,0]/%x[0,0]/%x[1,0] | ||
U12:%x[0,0]/%x[1,0]/%x[2,0] | ||
四元特征模板 | U13:%x[-2,0]/%x[-1,0]/%x[0,0]/%x[1,0] | |
U14:%x[-1,0]/%x[0,0]/%x[1,0]/%x[2,0] | ||
五元特征模板 | U15:%x[-2,0]/%x[-1,0]/%x[0,0]/%x[1,0]/%x[2,0] |
常识名称 | 常识属性 | 属性值 | 属性值的数量或比例关系 |
---|---|---|---|
骰子 | 点数 | 1;2;3;4;5;6 | 1∶1∶1∶1∶1∶1 |
硬币 | 面 | 正面向上;反面向上 | 1∶1 |
钥匙 | 状态 | 打开锁;打不开锁 | 1∶1 |
Tab. 5 Commonsense knowledge base of situation for understanding of classical probability word problems (part)
常识名称 | 常识属性 | 属性值 | 属性值的数量或比例关系 |
---|---|---|---|
骰子 | 点数 | 1;2;3;4;5;6 | 1∶1∶1∶1∶1∶1 |
硬币 | 面 | 正面向上;反面向上 | 1∶1 |
钥匙 | 状态 | 打开锁;打不开锁 | 1∶1 |
常识名称 | 同义词 | 常识属性 | 属性值 | 属性值描述 |
---|---|---|---|---|
和 | 之和; | 运算 | r1;r2 | r1+r2 |
偶数 | — | 数值 | r1 | r1%2==0 |
大于 | 大;高于;超过; | 比较 | r1;r2 | r1>r2 |
与 | — | 逻辑运算 | r1;r2 | r1|r2 |
Tab. 6 Commonsense knowledge base of math for understanding of classical probability word problems (part)
常识名称 | 同义词 | 常识属性 | 属性值 | 属性值描述 |
---|---|---|---|---|
和 | 之和; | 运算 | r1;r2 | r1+r2 |
偶数 | — | 数值 | r1 | r1%2==0 |
大于 | 大;高于;超过; | 比较 | r1;r2 | r1>r2 |
与 | — | 逻辑运算 | r1;r2 | r1|r2 |
特征组合 | 窗口大小为3 | 窗口大小为5 | ||||||
---|---|---|---|---|---|---|---|---|
一元 | 二元 | 三元 | 一元 | 二元 | 三元 | 四元 | 五元 | |
W | 0.858 4 | 0.766 3 | 0.530 2 | 0.8886 | 0.800 0 | 0.644 6 | 0.418 3 | 0.217 2 |
W+P | 0.893 9 | 0.8943 | 0.887 0 | 0.891 9 | 0.889 4 | 0.882 0 | 0.884 9 | 0.890 0 |
W+Q | 0.892 5 | 0.891 2 | 0.892 1 | 0.891 4 | 0.8930 | 0.891 3 | 0.892 1 | 0.891 9 |
W+B | 0.890 0 | 0.890 1 | 0.890 1 | 0.886 8 | 0.888 0 | 0.888 3 | 0.890 2 | 0.8904 |
W+M | 0.887 9 | 0.888 0 | 0.888 6 | 0.887 5 | 0.886 8 | 0.887 7 | 0.887 8 | 0.8890 |
W+D | 0.891 3 | 0.890 2 | 0.890 9 | 0.887 7 | 0.888 9 | 0.8933 | 0.888 8 | 0.888 7 |
Tab. 7 F1-scores of recognition results of combinations of word feature and other features
特征组合 | 窗口大小为3 | 窗口大小为5 | ||||||
---|---|---|---|---|---|---|---|---|
一元 | 二元 | 三元 | 一元 | 二元 | 三元 | 四元 | 五元 | |
W | 0.858 4 | 0.766 3 | 0.530 2 | 0.8886 | 0.800 0 | 0.644 6 | 0.418 3 | 0.217 2 |
W+P | 0.893 9 | 0.8943 | 0.887 0 | 0.891 9 | 0.889 4 | 0.882 0 | 0.884 9 | 0.890 0 |
W+Q | 0.892 5 | 0.891 2 | 0.892 1 | 0.891 4 | 0.8930 | 0.891 3 | 0.892 1 | 0.891 9 |
W+B | 0.890 0 | 0.890 1 | 0.890 1 | 0.886 8 | 0.888 0 | 0.888 3 | 0.890 2 | 0.8904 |
W+M | 0.887 9 | 0.888 0 | 0.888 6 | 0.887 5 | 0.886 8 | 0.887 7 | 0.887 8 | 0.8890 |
W+D | 0.891 3 | 0.890 2 | 0.890 9 | 0.887 7 | 0.888 9 | 0.8933 | 0.888 8 | 0.888 7 |
特征组合 | Nam | Num | Inf_nam | Inf | Inf_num | Quan | Meth | Mean value |
---|---|---|---|---|---|---|---|---|
W | 0.864 | 0.842 | 0.928 | 0.914 | 0.871 | 0.929 | 0.980 | 0.904 |
W+P | 0.883 | 0.870 | 0.923 | 0.925 | 0.871 | 0.931 | 0.970 | 0.910 |
W+P+B | 0.892 | 0.871 | 0.925 | 0.940 | 0.891 | 0.930 | 0.975 | 0.918 |
W+P+B+Q | 0.886 | 0.876 | 0.918 | 0.937 | 0.902 | 0.929 | 0.975 | 0.918 |
W+P+B+Q+M | 0.897 | 0.879 | 0.933 | 0.940 | 0.902 | 0.931 | 0.980 | 0.923 |
W+P+B+Q+M+D | 0.923 | 0.894 | 0.921 | 0.956 | 0.918 | 0.937 | 1.000 | 0.936 |
Tab. 8 F1-scores of recognition results of different feature combinations
特征组合 | Nam | Num | Inf_nam | Inf | Inf_num | Quan | Meth | Mean value |
---|---|---|---|---|---|---|---|---|
W | 0.864 | 0.842 | 0.928 | 0.914 | 0.871 | 0.929 | 0.980 | 0.904 |
W+P | 0.883 | 0.870 | 0.923 | 0.925 | 0.871 | 0.931 | 0.970 | 0.910 |
W+P+B | 0.892 | 0.871 | 0.925 | 0.940 | 0.891 | 0.930 | 0.975 | 0.918 |
W+P+B+Q | 0.886 | 0.876 | 0.918 | 0.937 | 0.902 | 0.929 | 0.975 | 0.918 |
W+P+B+Q+M | 0.897 | 0.879 | 0.933 | 0.940 | 0.902 | 0.931 | 0.980 | 0.923 |
W+P+B+Q+M+D | 0.923 | 0.894 | 0.921 | 0.956 | 0.918 | 0.937 | 1.000 | 0.936 |
方法 | Nam | Num | Inf_nam | Inf | Inf_num | Quan | Meth | Mean value |
---|---|---|---|---|---|---|---|---|
MaxEnt | 0.750 | 0.554 | 0.813 | 0.847 | 0.514 | 0.496 | 0.897 | 0.695 9 |
BiLSTM-CRF | 0.833 | 0.811 | 0.881 | 0.903 | 0.840 | 0.901 | 0.932 | 0.871 6 |
传统CRF | 0.886 | 0.876 | 0.918 | 0.937 | 0.902 | 0.929 | 0.975 | 0.917 6 |
多维语法特征CRF | 0.923 | 0.894 | 0.921 | 0.956 | 0.918 | 0.937 | 1.000 | 0.935 6 |
Tab. 9 Comparison of F1-score with baseline methods
方法 | Nam | Num | Inf_nam | Inf | Inf_num | Quan | Meth | Mean value |
---|---|---|---|---|---|---|---|---|
MaxEnt | 0.750 | 0.554 | 0.813 | 0.847 | 0.514 | 0.496 | 0.897 | 0.695 9 |
BiLSTM-CRF | 0.833 | 0.811 | 0.881 | 0.903 | 0.840 | 0.901 | 0.932 | 0.871 6 |
传统CRF | 0.886 | 0.876 | 0.918 | 0.937 | 0.902 | 0.929 | 0.975 | 0.917 6 |
多维语法特征CRF | 0.923 | 0.894 | 0.921 | 0.956 | 0.918 | 0.937 | 1.000 | 0.935 6 |
方法 | |||
---|---|---|---|
MaxEnt | 23 | 258 | 0.081 9 |
BiLSTM-CRF | 66 | 215 | 0.234 9 |
传统CRF | 54 | 227 | 0.192 2 |
多维语法特征CRF | 87 | 194 | 0.309 6 |
常识库+MaxEnt | 77 | 204 | 0.274 0 |
常识库+BiLSTM-CRF | 159 | 122 | 0.565 8 |
常识库+多维语法特征CRF | 187 | 94 | 0.665 4 |
Tab. 10 Comparison of accuracy of word problem understanding with other methods
方法 | |||
---|---|---|---|
MaxEnt | 23 | 258 | 0.081 9 |
BiLSTM-CRF | 66 | 215 | 0.234 9 |
传统CRF | 54 | 227 | 0.192 2 |
多维语法特征CRF | 87 | 194 | 0.309 6 |
常识库+MaxEnt | 77 | 204 | 0.274 0 |
常识库+BiLSTM-CRF | 159 | 122 | 0.565 8 |
常识库+多维语法特征CRF | 187 | 94 | 0.665 4 |
1 | BOBROW D G. Natural language input for a computer problem solving system: AIM-066[R/OL]. (1964-03-30) [2021-10-21].. |
2 | CHIEU H L, NG H T. Named entity recognition with a maximum entropy approach[C]// Proceedings of the 7th Conference on Natural Language Learning at HLT-NAACL 2003. Stroudsburg, PA: ACL, 2003:160-163. 10.3115/1119176.1119199 |
3 | LEAMAN R, LU Z. TaggerOne: joint named entity recognition and normalization with semi-Markov models[J]. Bioinformatics, 2016, 32(18): 2839-2846. 10.1093/bioinformatics/btw343 |
4 | 殷章志,李欣子,黄德根,等. 融合字词模型的中文命名实体识别研究[J]. 中文信息学报, 2019, 33(11):95-100, 106. 10.3969/j.issn.1003-0077.2019.11.011 |
YIN Z Z, LI X Z, HUANG D G, et al. Chinese named entity recognition ensembled with character[J]. Journal of Chinese Information Processing, 2019, 33(11): 95-100, 106. 10.3969/j.issn.1003-0077.2019.11.011 | |
5 | SONG S L, ZHANG N, HUANG H T. Named entity recognition based on conditional random fields[J]. Cluster Computing, 2019, 22(3): 5195-5206. 10.1007/s10586-017-1146-3 |
6 | 冶忠林,贾真,尹红风. 多领域自然语言问句理解研究[J]. 计算机科学, 2017, 44(6):216-221, 254. 10.11896/j.issn.1002-137X.2017.06.036 |
YE Z L, JIA Z, YIN H F. Research on multi-domain natural language question understanding[J]. Computer Science, 2017, 44(6):216-221, 254. 10.11896/j.issn.1002-137X.2017.06.036 | |
7 | 谭红叶,武宇飞. 汉语阅读理解中词义判断题的解答研究[J]. 计算机科学, 2018, 45(6A): 72-74. 10.11896/j.issn.1002-137X.2018.Z6.014 |
TAN H Y, WU Y F. Answering word sense judgement questions in Chinese reading comprehension[J]. Computer Science, 2018, 45(6A): 72-74. 10.11896/j.issn.1002-137X.2018.Z6.014 | |
8 | HOFMANN T. Unsupervised learning by probabilistic latent semantic analysis[J]. Machine Learning, 2001, 42(1/2):177-196. 10.1023/a:1007617005950 |
9 | DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Stroudsburg, PA: ACL, 2019:4147-4186. 10.18653/v1/n18-2 |
10 | KADLEC R, SCHMID M, BAJGAR O, et al. Text understanding with the attention sum reader network[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2016:908-918. 10.18653/v1/p16-1086 |
11 | SEO M, KEMBHAVI A, FARHADI A, et al. Bidirectional attention flow for machine comprehension[EB/OL]. (2018-06-21) [2021-05-28].. |
12 | CHARNIAK E. Computer solution of calculus word problems[C]// Proceedings of the 1st International Joint Conference on Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers Inc., 1969: 303-316. |
13 | GELB J P. Experiments with a natural language problem-solving system[C]// Proceedings of the 2nd International Joint Conference on Artificial intelligence. San Francisco: Morgan Kaufmann Publishers Inc., 1971: 455-462. |
14 | KINTSCH W, GREENO J G. Understanding and solving word arithmetic problems[J]. Psychological Review, 1985, 92(1): 109-129. 10.1037/0033-295x.92.1.109 |
15 | IWANE N, TAKEUCHI A, OTSUKI S. A network intelligent educational system for arithmetic word problems[J]. Systems and Computers in Japan, 1997, 28(10): 30-39. 10.1002/(sici)1520-684x(199709)28:10<30::aid-scj4>3.0.co;2-d |
16 | 吴林静,劳传媛,范桂林,等. 一种规则与统计相结合的应用题句子语义角色识别方法[J]. 计算机应用研究, 2018, 35(8):2299-2303. 10.3969/j.issn.1001-3695.2018.08.015 |
WU L J, LAO C Y, FAN G L, et al. Hybrid method based on rules and statistics for semantic role annotation in math word problems[J]. Application Research of Computers, 2018, 35(8):2299-2303. 10.3969/j.issn.1001-3695.2018.08.015 | |
17 | SEO M, HAJISHIRZI H, FARHADI A, et al. Solving geometry problems: combining text and diagram interpretation[C]// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2015: 1466-1476. 10.18653/v1/d15-1171 |
18 | 张智慧. 基于SVM的初等数学问题自动分类的研究与应用[D]. 成都:电子科技大学, 2017. |
ZHANG Z H. Research and application of the automatic classification of elementary mathematical problems based on SVM[D]. Chengdu: University of Electronic Science and Technology of China, 2017. | |
19 | 吴宣乐. 基于句模的初等数学问题题意理解方法研究及应用[D]. 成都:电子科技大学, 2016. |
WU X L. Research and application of the approach to understanding elementary mathematical problems based on sentence framework[D]. Chengdu: University of Electronic Science and Technology of China, 2016. | |
20 | 高冰涛,张阳,刘斌. BioTrHMM:基于迁移学习的生物医学命名实体识别算法[J]. 计算机应用研究, 2019, 36(1):45-48. |
GAO B T, ZHANG Y, LIU B. BioTrHMM: named entity recognition algorithm based on transfer learning in biomedical texts[J]. Application Research of Computers, 2019, 36(1):45-48. | |
21 | AMARAL D O F, VIEIRA R. NERP-CRF: uma ferramenta para o reconhecimento de entidades nomeadas por meio de conditional random fields[J]. Linguamática, 2014, 6(1):41-49. |
22 | 冯蕴天,张宏军,郝文宁. 面向军事文本的命名实体识别[J]. 计算机科学, 2015, 42(7):15-18, 47. |
FENG Y T, ZHANG H J, HAO W N. Named entity recognition for military text[J]. Computer Science, 2015, 42(7):15-18, 47. | |
23 | 唐国强,高大启,阮彤,等. 融入语言模型和注意力机制的临床电子病历命名实体识别[J]. 计算机科学, 2020, 47(3):211-216. 10.11896/jsjkx.190200259 |
TANG G Q, GAO D Q, RUAN T, et al. Clinical electronic medical record named entity recognition incorporating language model[J]. Computer Science, 2020, 47(3):211-216. 10.11896/jsjkx.190200259 | |
24 | 董哲,邵若琦,陈玉梁,等. 基于BERT和对抗训练的食品领域命名实体识别[J]. 计算机科学, 2021, 48(5):247-253. 10.11896/jsjkx.200800181 |
DONG Z, SHAO R Q, CHEN Y L, et al. Named entity recognition in food field based on BERT and adversarial training[J]. Computer Science, 2021, 48(5):247-253. 10.11896/jsjkx.200800181 | |
25 | PIROVANI J P C, DE OLIVEIRA E. Portuguese named entity recognition using conditional random fields and local grammars[C]// Proceedings of the 11th International Conference on Language Resources and Evaluation. [S.l.]: European Language Resources Association, 2018:4452-4456. |
26 | 崔丹丹,刘秀磊,陈若愚,等. 基于Lattice LSTM的古汉语命名实体识别[J]. 计算机科学, 2020, 47(11A):18-22. |
CUI D D, LIU X L, CHEN R Y, et al. Named entity recognition in field of ancient Chinese based on lattice LSTM[J]. Computer Science, 2020, 47(11A):18-22. | |
27 | 刘飞飞,王志娟. 基于层次特征的藏文人名识别研究[J]. 计算机应用研究, 2018, 35(9):2583-2587, 2596. 10.3969/j.issn.1001-3695.2018.09.005 |
LIU F F, WANG Z J. Research on recognition of Tibetan names based on hierarchical features[J]. Application Research of Computers, 2018, 35(9):2583-2587, 2596. 10.3969/j.issn.1001-3695.2018.09.005 | |
28 | WONG W K, HSU S C, WU S H, et al. LIM-G: learner-initiating instruction model based on cognitive knowledge for geometry word problem comprehension[J]. Computers and Education, 2007, 48(4): 582-601. 10.1016/j.compedu.2005.03.009 |
29 | 刘清堂,杨炜钦,吴林静,等. 初等数学应用题题意理解中的常识库系统构建[J]. 计算机系统应用, 2020, 29(12):72-79. 10.15888/j.cnki.csa.007714 |
LIU Q T, YANG W Q, WU L J, et al. Constructing of commonsense knowledge base in problem understanding of elementary mathematics[J]. Computer Systems and Applications, 2020, 29(12):72-79. 10.15888/j.cnki.csa.007714 | |
30 | 张景中,李永彬. 几何定理机器证明三十年[J]. 系统科学与数学, 2009, 29(9):1155-1168. |
ZHANG J Z, LI Y B. Automatic theorem proving for three decades[J]. Journal of Systems Science and Mathematical Sciences, 2009, 29(9):1155-1168. | |
31 | JIE Z M, LU W. Dependency-guided LSTM-CRF for named entity recognition[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg, PA: ACL, 2019: 3862-3872. 10.18653/v1/d19-1399 |
32 | 张雪松,郭瑞强,黄德根. 基于依存关系的命名实体识别[J]. 中文信息学报, 2021, 35(6):63-73. 10.3969/j.issn.1003-0077.2021.06.007 |
ZHANG X S, GUO R Q, HUANG D G. Named entity recognition based on dependency[J]. Journal of Chinese Information Processing, 2021, 35(6): 63-73. 10.3969/j.issn.1003-0077.2021.06.007 | |
33 | LIU H, SINGH P. ConceptNet — a practical commonsense reasoning tool-kit[J]. BT Technology Journal, 2004, 22(4): 211-226. 10.1023/b:bttj.0000047600.45421.6d |
34 | SINGH P. The public acquisition of commonsense knowledge[R/OL]. (2002) [2021-10-21].. |
35 | LIU H, SINGH P. Commonsense reasoning in and over natural language[C]// Proceedings of the 2004 International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, LNCS 3215. Berlin: Springer, 2004: 293-306. |
36 | 张桂平,刁丽娜,王裴岩. 基于HowNet的航空术语语义知识库的构建[J]. 中文信息学报, 2014, 28(5):92-101. 10.3969/j.issn.1003-0077.2014.05.012 |
ZHANG G P, DIAO L N, WANG P Y. Construction of aviation terminology semantic knowledge base based on HowNet[J]. Journal of Chinese Information Processing, 2014, 28(5): 92-101. 10.3969/j.issn.1003-0077.2014.05.012 | |
37 | LAFFERTY J D, McCALLUM A, PEREIRA F C N. Conditional random fields: probabilistic models for segmenting and labeling sequence data[C]// Proceedings of the 18th International Conference on Machine Learning. San Francisco: Morgan Kaufmann Publishers Inc., 2001: 282-289. |
38 | National Institute of Standards and Technology. Introduction to information extraction[EB/OL]. (2005-03-08) [2021-05-28].. |
39 | SMITH B. Formal ontology, common sense and cognitive science[J]. International Journal of Human⁃Computer Studies, 1995, 43(5/6): 641-667. 10.1006/ijhc.1995.1067 |
40 | FOXVOG D. Cyc[M]// Theory and Applications of Ontology: Computer Applications. Dordrecht: Springer, 2010: 259-278. 10.1007/978-90-481-8847-5_12 |
41 | MILLER G A, BECKWITH R, FELLBAUM C, et al. Introduction to WordNet: an on-line lexical database[J]. International Journal of Lexicography, 1990, 3(4): 235-244. 10.1093/ijl/3.4.235 |
[1] | Yongfeng DONG, Jiaming BAI, Liqin WANG, Xu WANG. Chinese named entity recognition combining prior knowledge and glyph features [J]. Journal of Computer Applications, 2024, 44(3): 702-708. |
[2] | HU Tiantian, DAN Yabo, HU Jie, LI Xiang, LI Shaobo. News named entity recognition and sentiment classification based on attention-based bi-directional long short-term memory neural network and conditional random field [J]. Journal of Computer Applications, 2020, 40(7): 1879-1883. |
[3] | LIAO Bin, LI Haowen. Image depth estimation model based on atrous convolutional neural network [J]. Journal of Computer Applications, 2019, 39(1): 267-274. |
[4] | ZHOU Shuangshuang, XU Jin'an, CHEN Yufeng, ZHANG Yujie. New words detection method for microblog text based on integrating of rules and statistics [J]. Journal of Computer Applications, 2017, 37(4): 1044-1050. |
[5] | LIU Tong, HUANG Xiutian, MA Jianshe, SU Ping. Image labeling based on fully-connected conditional random field [J]. Journal of Computer Applications, 2017, 37(10): 2841-2846. |
[6] | WANG Ting, WANG Qi, HUANG Yueqi, YIN Yichao, GAO Ju. Automatic hyponymy extracting method based on symptom components [J]. Journal of Computer Applications, 2017, 37(10): 2999-3005. |
[7] | HUANG Nian'e, HUANG He, WANG Rujing. Agriculture-related product name extraction and category labeling based on ontology and conditional random field [J]. Journal of Computer Applications, 2017, 37(1): 233-238. |
[8] | LIU Chunli, LI Xiaoge, LIU Rui, FAN Xian, DU Liping. Chinese word segment based on character representation learning [J]. Journal of Computer Applications, 2016, 36(10): 2794-2798. |
[9] | ZHOU Xiang, LI Shaobo, YANG Guanci. Entity recognition of clothing commodity attributes [J]. Journal of Computer Applications, 2015, 35(7): 1945-1949. |
[10] | LIU Li, WANG Yongheng, WEI Hang. Fine-grained sentiment analysis oriented to product comment [J]. Journal of Computer Applications, 2015, 35(12): 3481-3486. |
[11] | MO Yiwen, JI Donghong, HUANG Jiangping. Slight-pause marks boundary identification based on conditional random field [J]. Journal of Computer Applications, 2015, 35(10): 2838-2842. |
[12] | YANG Yufei DAI Qi JIA Zhen YI Hongfeng. Weakly supervised method for attribute relation extraction [J]. Journal of Computer Applications, 2014, 34(1): 64-68. |
[13] | WANG Kejun LV Zhuowen SUN Guozhen YAN Tao. Human behavior recognition based on stratified fractal conditional random field [J]. Journal of Computer Applications, 2013, 33(04): 957-959. |
[14] | ZHANG Wei WANG Xi-li. Superpixel-based conditional random field for image classification [J]. Journal of Computer Applications, 2012, 32(05): 1272-1275. |
[15] | WANG Xi-jie. Analysis on Effect Range of Context in Chinese Word Segmentation based Word -position Tagging [J]. Journal of Computer Applications, 2012, 32(05): 1340-1342. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||