《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (10): 3047-3057.DOI: 10.11772/j.issn.1001-9081.2023101391
收稿日期:
2023-10-16
修回日期:
2024-01-31
接受日期:
2024-02-04
发布日期:
2024-10-15
出版日期:
2024-10-10
通讯作者:
过弋
作者简介:
蒋汶娟(1999—),女(土家族),湖北恩施人,硕士,主要研究方向:知识图谱推理、时序知识图谱问答基金资助:
Wenjuan JIANG1, Yi GUO1,2,3(), Jiaojiao FU1
Received:
2023-10-16
Revised:
2024-01-31
Accepted:
2024-02-04
Online:
2024-10-15
Published:
2024-10-10
Contact:
Yi GUO
About author:
JIANG Wenjuan, born in 1999, M. S. Her research interests include knowledge graph reasoning, temporal knowledge graph question answering.Supported by:
摘要:
在时序知识图谱问答(TKGQA)任务中,针对模型难以捕获并利用问句中隐含的时间信息增强模型的复杂问题推理能力的问题,提出一种融合图注意力的时序知识图谱推理问答(GACTR)模型。所提模型采用四元组形式的时序知识库(KB)进行预训练,同时引入图注意力网络(GAT)以有效捕获问句中隐式时间信息;通过与RoBERTa(Robustly optimized Bidirectional Encoder Representations from Transformers pretraining approach)模型训练的关系表示进行集成,进一步增强问句的时序关系表示;将该表示与预训练的时序知识图谱(TKG)嵌入相结合,以获得最高评分的实体或时间戳作为答案预测结果。在最大的基准数据集CRONQUESTIONS上的实验结果显示,GACTR模型在时序推理模式下能更好地捕获隐含时间信息,有效提升模型的复杂推理能力。与基线模型CRONKGQA(Knowledge Graph Question Answering on CRONQUESTIONS)相比,GACTR模型在处理复杂问题类型和时间答案类型上的Hits@1结果分别提升了34.6、13.2个百分点;与TempoQR(Temporal Question Reasoning)模型相比,分别提升了8.3、2.8个百分点。
中图分类号:
蒋汶娟, 过弋, 付娇娇. 融合图注意力的复杂时序知识图谱推理问答模型[J]. 计算机应用, 2024, 44(10): 3047-3057.
Wenjuan JIANG, Yi GUO, Jiaojiao FU. Reasoning question answering model of complex temporal knowledge graph with graph attention[J]. Journal of Computer Applications, 2024, 44(10): 3047-3057.
类别 | 类型 | 训练集样本数 | 验证集样本数 | 测试集样本数 |
---|---|---|---|---|
问题 类型 | Simple Entity | 90 651 | 7 745 | 7 812 |
Simple Time | 61 471 | 5 197 | 5 046 | |
Before/After | 23 869 | 1 982 | 2 151 | |
First/Last | 118 556 | 11 198 | 11 159 | |
Time_Join | 55 453 | 3 878 | 3 832 | |
答案 类型 | Entity Answer | 225 672 | 19 362 | 19 524 |
Time Answer | 124 328 | 10 638 | 13 476 | |
总样本数 | 350 000 | 30 000 | 30 000 |
表1 数据集数据统计
Tab. 1 Statistical overview of dataset
类别 | 类型 | 训练集样本数 | 验证集样本数 | 测试集样本数 |
---|---|---|---|---|
问题 类型 | Simple Entity | 90 651 | 7 745 | 7 812 |
Simple Time | 61 471 | 5 197 | 5 046 | |
Before/After | 23 869 | 1 982 | 2 151 | |
First/Last | 118 556 | 11 198 | 11 159 | |
Time_Join | 55 453 | 3 878 | 3 832 | |
答案 类型 | Entity Answer | 225 672 | 19 362 | 19 524 |
Time Answer | 124 328 | 10 638 | 13 476 | |
总样本数 | 350 000 | 30 000 | 30 000 |
问题类型 | 问题子类型 | 问题示例 |
---|---|---|
Simple | Simple Entity | Which award did Brad Pitt receive in 2001? |
Simple Time | When was LeonAdolphe Amette the archbishop of Paris? | |
Complex | Before/After | Who was the senator of Ohio before Homer Ramey? |
First/Last | Who last held Minister of Finance of Norway’s position? | |
Time_Join | Who was speaker of the house in ESC 2005? |
表2 CRONQUESTIONS中不同类型问题的示例
Tab. 2 Example questions for different types from CRONQUESTIONS
问题类型 | 问题子类型 | 问题示例 |
---|---|---|
Simple | Simple Entity | Which award did Brad Pitt receive in 2001? |
Simple Time | When was LeonAdolphe Amette the archbishop of Paris? | |
Complex | Before/After | Who was the senator of Ohio before Homer Ramey? |
First/Last | Who last held Minister of Finance of Norway’s position? | |
Time_Join | Who was speaker of the house in ESC 2005? |
实验环境 | 具体信息 |
---|---|
操作系统 | Ubuntu 18.03 |
内存 | DDR4 64 GB |
CPU | Intel Xeon Gold 5218 |
GPU | GeForce RTX 3090 |
开发语言 | Python 3.9.0 |
深度学习框架 | PyTorch 1.9 |
表3 实验环境信息
Tab. 3 Experimental environment information
实验环境 | 具体信息 |
---|---|
操作系统 | Ubuntu 18.03 |
内存 | DDR4 64 GB |
CPU | Intel Xeon Gold 5218 |
GPU | GeForce RTX 3090 |
开发语言 | Python 3.9.0 |
深度学习框架 | PyTorch 1.9 |
模型 | Hits@1 | Hits@10 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
总体 | 问题类型 | 答案类型 | 总体 | 问题类型 | 答案类型 | |||||
Complex | Simple | Entity | Time | Complex | Simple | Entity | Time | |||
BERT | 0.071 | 0.086 | 0.052 | 0.077 | 0.060 | 0.213 | 0.205 | 0.225 | 0.192 | 0.253 |
RoBERTa | 0.070 | 0.086 | 0.050 | 0.082 | 0.048 | 0.202 | 0.192 | 0.215 | 0.186 | 0.231 |
KnowBERT | 0.070 | 0.083 | 0.051 | 0.081 | 0.048 | 0.201 | 0.189 | 0.217 | 0.185 | 0.230 |
EmbedKGQA | 0.288 | 0.286 | 0.290 | 0.411 | 0.057 | 0.672 | 0.632 | 0.725 | 0.850 | 0.341 |
T-EaE-add | 0.278 | 0.257 | 0.306 | 0.313 | 0.213 | 0.663 | 0.614 | 0.729 | 0.662 | 0.665 |
T-EaE-replace | 0.288 | 0.257 | 0.329 | 0.318 | 0.231 | 0.678 | 0.623 | 0.753 | 0.668 | 0.698 |
CRONKGQA | 0.647 | 0.392 | 0.987 | 0.699 | 0.549 | 0.884 | 0.802 | 0.992 | 0.898 | 0.857 |
EntityQR | 0.745 | 0.562 | 0.990 | 0.831 | 0.585 | 0.944 | 0.906 | 0.993 | 0.962 | 0.910 |
TempoQR-Soft | 0.799 | 0.655 | 0.990 | 0.876 | 0.653 | 0.957 | 0.930 | 0.993 | 0.972 | 0.929 |
CTRN-Soft | 0.806 | 0.668 | 0.990 | 0.877 | 0.673 | 0.955 | 0.927 | 0.993 | 0.969 | 0.929 |
TMA | 0.784 | 0.632 | 0.987 | 0.792 | 0.743 | 0.943 | 0.904 | 0.995 | 0.947 | 0.936 |
GACTR-Soft | 0.848 | 0.738 | 0.994 | 0.937 | 0.681 | 0.957 | 0.927 | 0.997 | 0.986 | 0.940 |
表4 基线模型和本文模型在CRONQUESTIONS数据集上的Hits@1和Hits@10值
Tab. 4 Hits@1 and Hits@10 values of baseline models and proposed model on CRONQUESTIONS dataset
模型 | Hits@1 | Hits@10 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
总体 | 问题类型 | 答案类型 | 总体 | 问题类型 | 答案类型 | |||||
Complex | Simple | Entity | Time | Complex | Simple | Entity | Time | |||
BERT | 0.071 | 0.086 | 0.052 | 0.077 | 0.060 | 0.213 | 0.205 | 0.225 | 0.192 | 0.253 |
RoBERTa | 0.070 | 0.086 | 0.050 | 0.082 | 0.048 | 0.202 | 0.192 | 0.215 | 0.186 | 0.231 |
KnowBERT | 0.070 | 0.083 | 0.051 | 0.081 | 0.048 | 0.201 | 0.189 | 0.217 | 0.185 | 0.230 |
EmbedKGQA | 0.288 | 0.286 | 0.290 | 0.411 | 0.057 | 0.672 | 0.632 | 0.725 | 0.850 | 0.341 |
T-EaE-add | 0.278 | 0.257 | 0.306 | 0.313 | 0.213 | 0.663 | 0.614 | 0.729 | 0.662 | 0.665 |
T-EaE-replace | 0.288 | 0.257 | 0.329 | 0.318 | 0.231 | 0.678 | 0.623 | 0.753 | 0.668 | 0.698 |
CRONKGQA | 0.647 | 0.392 | 0.987 | 0.699 | 0.549 | 0.884 | 0.802 | 0.992 | 0.898 | 0.857 |
EntityQR | 0.745 | 0.562 | 0.990 | 0.831 | 0.585 | 0.944 | 0.906 | 0.993 | 0.962 | 0.910 |
TempoQR-Soft | 0.799 | 0.655 | 0.990 | 0.876 | 0.653 | 0.957 | 0.930 | 0.993 | 0.972 | 0.929 |
CTRN-Soft | 0.806 | 0.668 | 0.990 | 0.877 | 0.673 | 0.955 | 0.927 | 0.993 | 0.969 | 0.929 |
TMA | 0.784 | 0.632 | 0.987 | 0.792 | 0.743 | 0.943 | 0.904 | 0.995 | 0.947 | 0.936 |
GACTR-Soft | 0.848 | 0.738 | 0.994 | 0.937 | 0.681 | 0.957 | 0.927 | 0.997 | 0.986 | 0.940 |
图4 大模型对实验中采用的提示模板(GPT使用对应英文版)
Fig. 4 Prompt templates used in comparative experiments of large models (for GPT, using the corresponding English version)
模型 | Before/After | First/Last | Time_Join | Complex |
---|---|---|---|---|
T-EaE-replace | 0.256 | 0.288 | 0.168 | 0.257 |
CRONKGQA | 0.288 | 0.371 | 0.511 | 0.392 |
EntityQR | 0.540 | 0.493 | 0.833 | 0.562 |
TempoQR-Soft | 0.670 | 0.570 | 0.894 | 0.655 |
CTRN-Soft | 0.680 | 0.584 | 0.907 | 0.668 |
TMA | 0.581 | 0.627 | 0.675 | 0.632 |
GACTR-Soft | 0.842 | 0.656 | 0.920 | 0.738 |
表5 各模型对不同复杂问题类型上的Hits@1值
Tab. 5 Hits@1 values of various models for different types of complex questions
模型 | Before/After | First/Last | Time_Join | Complex |
---|---|---|---|---|
T-EaE-replace | 0.256 | 0.288 | 0.168 | 0.257 |
CRONKGQA | 0.288 | 0.371 | 0.511 | 0.392 |
EntityQR | 0.540 | 0.493 | 0.833 | 0.562 |
TempoQR-Soft | 0.670 | 0.570 | 0.894 | 0.655 |
CTRN-Soft | 0.680 | 0.584 | 0.907 | 0.668 |
TMA | 0.581 | 0.627 | 0.675 | 0.632 |
GACTR-Soft | 0.842 | 0.656 | 0.920 | 0.738 |
模型 | Before/After | First/Last | Time_Join | Complex |
---|---|---|---|---|
GACTR-Soft | 0.910 | 0.783 | 0.733 | 0.807 |
GPT3.5 | 0.400 | 0.766 | 0.480 | 0.548 |
GLM3-6B | 0.060 | 0.100 | 0.020 | 0.062 |
表6 大模型和GACTR模型在不同复杂问题类型上的Hits@1值(非全量数据集)
Tab. 6 Hits@1 values of large-scale models and GACTR model on different types of complex questions (partial dataset)
模型 | Before/After | First/Last | Time_Join | Complex |
---|---|---|---|---|
GACTR-Soft | 0.910 | 0.783 | 0.733 | 0.807 |
GPT3.5 | 0.400 | 0.766 | 0.480 | 0.548 |
GLM3-6B | 0.060 | 0.100 | 0.020 | 0.062 |
序号 | 问题 | 问题类型 | GACTR | GPT3.5 | GLM3-6B | 正确答案 | ||||
---|---|---|---|---|---|---|---|---|---|---|
答案 | 答案 | 类型 | 时间词 | 答案 | 类型 | 时间词 | ||||
1 | Who was the President of the American Philological Association before 2012 Olympics? | Before/ After | Josiah Ober | Henry Rushton … | 实体 | Before | Ivan Mortimer Linforth | 实体 | Before | Josiah Ober |
2 | Who held the position of City councillor of Palafrugell after Joan Cama i Serra? | Before/ After | Francesc Alsius i Granés | Begonya Montalban i Vilas | 实体 | After | Francesc Alsius i Granés | 实体 | After | Francesc Alsius i Granés |
3 | When was the first time Jack Midson was playing in The Shrimpers? | First/Last | 2010 | 2010 | 时间 | First | Jack Midson | 实体 | First | 2010 |
4 | Which was the latest award that Virginia R. Grace received? | First/Last | Gold Medal of the … | Gold Medal of the … | 实体 | Latest | Virginia Grace | 实体 | Last | Gold Medal of the … |
5 | What person held the position of Agriculture Minister of Israel in ESC 2005? | Time_Join | Yisrael Katz | Yisrael Katz | 实体 | In | Pinhas Lavon | 实体 | Last | Yisrael Katz |
6 | Who was the Danish Defence Minister during 1956 Winter Olympics? | Time_Join | Poul Hansen | Poul Hansen | 实体 | During | Poul Hansen | 实体 | First | Poul Hansen |
表7 大模型典型错误问答案例(省略了过长的实体名)
Tab. 7 Typical examples of large-scale model’s wrong question answering (excessively long entity names omitted)
序号 | 问题 | 问题类型 | GACTR | GPT3.5 | GLM3-6B | 正确答案 | ||||
---|---|---|---|---|---|---|---|---|---|---|
答案 | 答案 | 类型 | 时间词 | 答案 | 类型 | 时间词 | ||||
1 | Who was the President of the American Philological Association before 2012 Olympics? | Before/ After | Josiah Ober | Henry Rushton … | 实体 | Before | Ivan Mortimer Linforth | 实体 | Before | Josiah Ober |
2 | Who held the position of City councillor of Palafrugell after Joan Cama i Serra? | Before/ After | Francesc Alsius i Granés | Begonya Montalban i Vilas | 实体 | After | Francesc Alsius i Granés | 实体 | After | Francesc Alsius i Granés |
3 | When was the first time Jack Midson was playing in The Shrimpers? | First/Last | 2010 | 2010 | 时间 | First | Jack Midson | 实体 | First | 2010 |
4 | Which was the latest award that Virginia R. Grace received? | First/Last | Gold Medal of the … | Gold Medal of the … | 实体 | Latest | Virginia Grace | 实体 | Last | Gold Medal of the … |
5 | What person held the position of Agriculture Minister of Israel in ESC 2005? | Time_Join | Yisrael Katz | Yisrael Katz | 实体 | In | Pinhas Lavon | 实体 | Last | Yisrael Katz |
6 | Who was the Danish Defence Minister during 1956 Winter Olympics? | Time_Join | Poul Hansen | Poul Hansen | 实体 | During | Poul Hansen | 实体 | First | Poul Hansen |
问题 类型 | 问题 | 时间关系 描述式 | GACTR | TempoQR | GRONKGQA | 正确答案 |
---|---|---|---|---|---|---|
Before/ After | Who was the United States Energy Secretary after Hazel R. O’Leary | Who was the Q1029968 after Q465586 | Bill Richard son(0.677), Spencer Abraham(0.134), Samuel Bodman(0.117), Steven Chu(0.050), Ernest Moniz(0.005) | James R.Schlesinger(0.100), Ernest Moniz(0.0764), James D. Watkins(0.0431), Hazel R. O’Leary(0.040), Samuel Bodman(0.0312) | 1836(0.017), 1806(0.014), 1845(0.011), 1835(0.009), 1842(0.009) | Bill Richardson |
First/ Last | Title of the award first award received by Hans Chemin-Petit | Title of the award first award received by Q1578970 | Berliner Kunstpreis(0.234), Howard N. P …(0.133), Ernst Reuter Medal(0.090), Grand Cross of …(0.070), Knight Grand Cross…(0.045) | Canada’s Walk…(0.308), Grammy Hall…(0.190), GrammyLifetime…(0.099), PraemiumImperiale(0.070), Legion of Honour(0.039) | Henry Ⅳ of France(0.0004), Samuel Schmid(0.0003), award(0.0003), Boris Alexandro…(0.0002), Royal Consort of…(0.0002) | Berliner Kunstpreis |
Time_ Join | Who held the position of Chairman of Ways and Means during Eurovision Song Contest 2005 | Who held the position of Q5068087 during Q10151 | Michael Lord(0.593), Sylvia Heal(0.355), Dawn Primarolo(0.0373), Nigel Evans(0.011), Yvette Cooper(0.0004) | George Thomas(0.082), Oscar Murton(0.054), Bernard Weatherill(0.030), Robert Grant-Ferris(0.029), Barbara Castle(0.024) | 200304 La Liga(0.0002), De Montfort …(0.0002), Heiner Zieschang(0.0002), Graham Westley(0.0002), Juan Ojeda(0.0002) | Alan Haselhurst, Sylvia Heal; Michael Lord |
表8 3种模型的典型错误问答案例(省略了过长的实体名)
Tab. 8 Typical examples of wrong question answering of three models (excessively long entity names omitted)
问题 类型 | 问题 | 时间关系 描述式 | GACTR | TempoQR | GRONKGQA | 正确答案 |
---|---|---|---|---|---|---|
Before/ After | Who was the United States Energy Secretary after Hazel R. O’Leary | Who was the Q1029968 after Q465586 | Bill Richard son(0.677), Spencer Abraham(0.134), Samuel Bodman(0.117), Steven Chu(0.050), Ernest Moniz(0.005) | James R.Schlesinger(0.100), Ernest Moniz(0.0764), James D. Watkins(0.0431), Hazel R. O’Leary(0.040), Samuel Bodman(0.0312) | 1836(0.017), 1806(0.014), 1845(0.011), 1835(0.009), 1842(0.009) | Bill Richardson |
First/ Last | Title of the award first award received by Hans Chemin-Petit | Title of the award first award received by Q1578970 | Berliner Kunstpreis(0.234), Howard N. P …(0.133), Ernst Reuter Medal(0.090), Grand Cross of …(0.070), Knight Grand Cross…(0.045) | Canada’s Walk…(0.308), Grammy Hall…(0.190), GrammyLifetime…(0.099), PraemiumImperiale(0.070), Legion of Honour(0.039) | Henry Ⅳ of France(0.0004), Samuel Schmid(0.0003), award(0.0003), Boris Alexandro…(0.0002), Royal Consort of…(0.0002) | Berliner Kunstpreis |
Time_ Join | Who held the position of Chairman of Ways and Means during Eurovision Song Contest 2005 | Who held the position of Q5068087 during Q10151 | Michael Lord(0.593), Sylvia Heal(0.355), Dawn Primarolo(0.0373), Nigel Evans(0.011), Yvette Cooper(0.0004) | George Thomas(0.082), Oscar Murton(0.054), Bernard Weatherill(0.030), Robert Grant-Ferris(0.029), Barbara Castle(0.024) | 200304 La Liga(0.0002), De Montfort …(0.0002), Heiner Zieschang(0.0002), Graham Westley(0.0002), Juan Ojeda(0.0002) | Alan Haselhurst, Sylvia Heal; Michael Lord |
方法 | Hits@1 | |||
---|---|---|---|---|
Before/After | First/last | Time_Join | Complex | |
GACTR | 0.842 | 0.656 | 0.920 | 0.738 |
w/o Multi-Head | 0.795 | 0.535 | 0.870 | 0.642 |
w/o GAT | 0.739 | 0.642 | 0.921 | 0.629 |
w/o CNN | 0.642 | 0.502 | 0.629 | 0.548 |
w/o 集成模型 | 0.605 | 0.630 | 0.856 | 0.555 |
w/o 时序评分 | 0.650 | 0.569 | 0.852 | 0.643 |
表9 消融实验结果
Tab. 9 Results of ablation experiments
方法 | Hits@1 | |||
---|---|---|---|---|
Before/After | First/last | Time_Join | Complex | |
GACTR | 0.842 | 0.656 | 0.920 | 0.738 |
w/o Multi-Head | 0.795 | 0.535 | 0.870 | 0.642 |
w/o GAT | 0.739 | 0.642 | 0.921 | 0.629 |
w/o CNN | 0.642 | 0.502 | 0.629 | 0.548 |
w/o 集成模型 | 0.605 | 0.630 | 0.856 | 0.555 |
w/o 时序评分 | 0.650 | 0.569 | 0.852 | 0.643 |
1 | JIA Z, ABUJABAL A, ROY R S, et al. TEQUILA: temporal question answering over knowledge bases[C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM, 2018:1807-1810. |
2 | LIU Y, MA Y, HILDEBRANDT M, et al. TLogic: temporal logical rules for explainable link forecasting on temporal knowledge graphs[C]// Proceedings of the 2022 AAAI Conference on Artificial Intelligence. Menlo Park: AAAI Press, 2022: 4120-4127. |
3 | SAXENA A, CHAKRABARTI S, TALUKDAR P. Question answering over temporal knowledge graphs[C] // Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Stroudsburg: ACL, 2021:6663-6676. |
4 | MAVROMATIS C, SUBRAMANYAM P L, IOANNIDIS V N, et al. TempoQR: temporal question reasoning over knowledge graphs[C]// Proceedings of the 36th AAAI Conference on Artificial Intelligence. Menlo Park: AAAI Press, 2021:5825-5833. |
5 | LACROIX T, OBOZINSKI G, USUNIER N.Tensor decompositions for temporal knowledge base completion [EB/OL]. (2020-04-10)[2023-10-01]. . |
6 | LIU Y, OTT M, GOYAL N, et al. RoBERTa: a robustly optimized BERT pretraining approach [EB/OL]. (2019-07-26) [2023-11-02]. . |
7 | CHEN Z, ZHAO X, LIAO J, et al. Temporal knowledge graph question answering via subgraph reasoning[J]. Knowledge-Based Systems, 2022, 251: 109134. |
8 | JIANG T, LIU T, GE T, et al. Towards time-aware knowledge graph completion[C]// Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers. [S.l.]: The COLING 2016 Organizing Committee, 2016: 1715-1724. |
9 | LEBLAY J, CHEKOL M W. Deriving validity time in knowledge graph[C]// Companion Proceedings of the Web Conference 2018. Republic and Canton of Geneva, Switzerland: International World Wide Web Conferences Steering Committee, 2018: 1771-1776. |
10 | BORDES A, USUNIER N, GARCIA-DURÁN A, et al. Translating embeddings for modeling multi-relational data[C]// Proceedings of the 26th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2013:2787-2795. |
11 | DASGUPTA S S, RAY S N, TALUKDAR P. HyTE: hyperplane-based temporally aware knowledge graph embedding[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2018: 2001-2011. |
12 | GOEL R, KAZEMI S M, BRUBAKER M, et al. Diachronic embedding for temporal knowledge graph completion[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Menlo Park: AAAI Press, 2020: 3988-3995. |
13 | TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[C]// Proceedings of the 33rd International Conference on Machine Learning. Stroudsburg: ACL, 2016:2071-2080. |
14 | SHAO P, ZHANG D, YANG G, et al. Tucker decomposition-based temporal knowledge graph completion[J]. Knowledge-Based Systems, 2022, 238: 107841. |
15 | SAXENA A, TRIPATHI A, TALUKDAR P. Improving multi-hop question answering over knowledge graphs using knowledge base embeddings[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 4498-4507. |
16 | CHEN Z, LIAO J, ZHAO X. Multi-granularity temporal question answering over knowledge graphs [C]// Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg: ACL, 2023:11378-11392. |
17 | LIU Y, LIANG D, FANG F, et al. Time-aware multiway adaptive fusion network for temporal knowledge graph question answering[C]// Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2023: 1-5. |
18 | SHANG C, WANG G, QI P, et al. Improving time sensitivity for question answering over temporal knowledge graphs[C]// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2022:8017-8026. |
19 | JIAO S, ZHU Z, WU W, et al. An improving reasoning network for complex question answering over temporal knowledge graphs[J]. Applied Intelligence, 2023, 53: 8195-8208. |
20 | VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[EB/OL]. (2017-10-30) [2023-10-01]. . |
21 | WANG X, HE X, CAO Y, et al. KGAT: knowledge graph attention network for recommendation[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2019:950-958. |
22 | ZHANG Z, ZHUANG F, ZHU H, et al. Relational graph neural network with hierarchical attention for knowledge graph completion[C]// Proceedings of the 2020 AAAI Conference on Artificial Intelligence. Menlo Park: AAAI Press, 2020: 9612-9619. |
23 | WANG Y, WANG H, HE J, et al. TAGAT: type-aware graph attention networks for reasoning over knowledge graphs[J]. Knowledge-Based Systems, 2021, 233: 107500. |
24 | FÉVRY T, SOARES L B, FitzGERALD N, et al. Entities as experts: sparse memory access with entity supervision[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2020: 4937-4951. |
25 | 张文豪,徐贞顺,刘纳,等. 知识图谱补全方法研究综述[J].计算机工程与应用,2024,60(12):61-73. |
ZHANG W H, XU Z S, LIU N, et al. A survey on knowledge graph completion methods[J]. Computer Engineering and Applications, 2024, 60(12):61-73. | |
26 | DONG Q, LI L, DAI D, et al. A survey for in-context learning [EB/OL]. (2022-12-31) [2023-10-01]. . |
27 | 张鹤译,王鑫,韩立帆,等. 大语言模型融合知识图谱的问答系统研究 [J]. 计算机科学与探索, 2023, 17(10): 2377-2388. |
ZHANG H Y, WANG X, HAN L F, et al.Research on question answering system on joint of knowledge graph and large language models[J]. Journal of Frontiers of Computer Science & Technology, 2023, 17(10): 2377-2388. |
[1] | 杨航, 李汪根, 张根生, 王志格, 开新. 基于图神经网络的多层信息交互融合算法用于会话推荐[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2719-2725. |
[2] | 柯添赐, 刘建华, 孙水华, 郑智雄, 蔡子杰. 融合强关联依赖和简洁语法的方面级情感分析模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1786-1795. |
[3] | 郭磊, 贾真, 李天瑞. 面向方面级情感分析的交互式关系图注意力网络[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 696-701. |
[4] | 徐大鹏, 侯新民. 基于网络结构设计的图神经网络特征选择方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 663-670. |
[5] | 王利琴, 张特, 许智宏, 董永峰, 杨国伟. 融合实体语义及结构信息的知识图谱推理[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3371-3378. |
[6] | 邓金科, 段文杰, 张顺香, 汪雨晴, 李书羽, 李嘉伟. 基于提示增强与双图注意力网络的复杂因果关系抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3081-3089. |
[7] | 樊海玮, 鲁芯丝雨, 张丽苗, 安毅生. 融合知识图谱和图注意力网络的引文推荐算法[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2420-2425. |
[8] | 郑智雄, 刘建华, 孙水华, 徐戈, 林鸿辉. 融合多窗口局部信息的方面级情感分析模型[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1796-1802. |
[9] | 隋佳宏, 毛莺池, 于慧敏, 王子成, 平萍. 基于图注意力网络的全局图像描述生成方法[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1409-1415. |
[10] | 吕学强, 张煜楠, 韩晶, 崔运鹏, 李欢. 融合边特征与注意力的表格结构识别模型[J]. 《计算机应用》唯一官方网站, 2023, 43(3): 752-758. |
[11] | 倪苒岩, 张轶. 基于视频时空特征的行为识别方法[J]. 《计算机应用》唯一官方网站, 2023, 43(2): 521-528. |
[12] | 汪锦云, 向阳. 基于关键词图表示的文本语义去重算法[J]. 《计算机应用》唯一官方网站, 2023, 43(10): 3070-3076. |
[13] | 杨世刚, 刘勇国. 融合语料库特征与图注意力网络的短文本分类方法[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1324-1329. |
[14] | 焦守龙, 段友祥, 孙歧峰, 庄子浩, 孙琛皓. 融合实体描述信息和邻居节点特征的知识表示学习方法[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1050-1056. |
[15] | 薛海涛, 王莉, 杨延杰, 廉飚. 基于用户传播网络与消息内容融合的谣言检测模型[J]. 《计算机应用》唯一官方网站, 2021, 41(12): 3540-3545. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||