基于知识图谱的智能问答意图识别联合模型

doi:10.3778/j.issn.1002-8331.2206-0419

摘要/Abstract

摘要： 针对现有意图识别联合模型在专业领域知识图谱问答中容易发生识别领域实体以及问句分类错误的情况，提出一个结合了领域知识图谱的意图识别联合模型。该模型有三步，将领域知识图谱中实体对应的本体标签以及本体间关系导入训练数据集，形成包含本体标签的知识文本以及额外包含本体关系的知识文本图；通过字符级嵌入和位置信息嵌入将包含了本体标签的知识文本转化成嵌入表示并依据知识文本图创建实体关系可视矩阵，明确知识文本各成分的相关程度；将嵌入表示和实体关系可视矩阵输入模型编码层进行模型的训练。以高速列车领域知识图谱为例，经过准确率和召回率的验证，以该方法训练出的模型在高速列车领域问答数据集的意图识别任务上取得了更好的表现。

关键词: 知识图谱智能问答, 意图识别, 联合模型

Abstract: Aiming at the situation that the existing joint model of intention recognition is prone to identify domain entities and question classification errors in the question answering of professional domain knowledge atlas, a joint model of intention recognition combined with domain knowledge atlas is proposed. The model has three steps. The ontology labels corresponding to entities in the domain knowledge map and the relationships between ontologies are imported into the training data set to form the knowledge text containing ontology labels and the knowledge text map containing additional ontology relationships. The knowledge text containing ontology tags is transformed into embedded representation through character level embedding and location information embedding, and the entity relationship visual matrix is created according to the knowledge text graph to clarify the correlation degree of each component of the knowledge text. The embedded representation and entity relationship visual matrix are input into the model coding layer for model training. Taking the high-speed train domain knowledge map as an example, through the verification of accuracy and recall, the model trained by this method has achieved better performance in the intention recognition task of the high-speed train domain question and answer datasets.

Key words: intelligent Q &, A, intention recognition, joint model

马自力, 王淑营, 张海柱, 黎荣. 基于知识图谱的智能问答意图识别联合模型[J]. 计算机工程与应用, 2023, 59(6): 171-178.

MA Zili, WANG Shuying, ZHANG Haizhu, LI Rong. Joint Model of Intelligent Q&A Intent Recognition Based on Knowledge Graph[J]. Computer Engineering and Applications, 2023, 59(6): 171-178.

参考文献

[1] 韩东方，吐尔地·托合提，艾斯卡尔·艾木都拉.问答系统中问句分类方法研究综述[J].计算机工程与应用，2021，57（6）：10-21.
HAN D F，TURDY TOHETI，ASKAR HAMDULLA.Surrey on question classification method in question answering system[J].Computer Engineering and Applications，2021，57（6）：10-21.
[2] 刘娇，李艳玲.人机对话系统中意图识别方法综述[J].计算机工程与应用，2019，55（12）：1-7.
LIU J，LI Y L.Review of intent detection methods in human-machine dialogue system[J].Computer Engineering and Applications，2019，55（12）：1-7.
[3] 侯丽仙，李艳玲，李成城.面向任务口语理解研究现状综述[J].计算机工程与应用，2019，55（11）：7-15.
HOU L X，LI Y L，LI C C.Review of research on task-oriented spoken language understanding[J].Computer Engineering and Applications，2019，55（11）：7-15.
[4] GOO C W，GAO G，HSU Y K，et al.Slot-gated modeling for joint slot filling and intent prediction[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies，2018.
[5] 李慧颖，赵满，余文麒.面向知识库问答的多注意力RNN关系链接方法[J].东南大学学报（英文版），2020，36（4）：385-392.
LI H Y，ZHAO M，YU W Q.A multi-attention RNN-based relation linking approach for question answering over knowledge base[J].Journal of Southeast University（English Edition），2020，36（4）：385-392.
[6] 彭敏，姚亚兰，谢倩倩，等.基于带注意力机制CNN的联合知识表示模型[J].中文信息学报，2019，33（2）：51-58.
PENG M，YAO Y L，XIE Q Q，et al.Knowledge representation learning for joint structural and textual embedding via attention-based CNN[J].Journal of Chinese Information Processing，2019，33（2）：51-58.
[7] CHEN Q，ZHUO Z，WANG W.BERT for joint intent classification and slot filling[J].arXiv：1902.10909，2019.
[8] GANGADHARAIAH R，NARAYANASWAMY B.Joint multiple intent detection and slot labeling for goal-oriented dialog[C]//Proceedings of the 2019 Conference of the North，2019.
[9] SUN Y，WANG S H，LI Y K.ERNIE：enhanced representation through knowledge integration[J].arXiv：1904.09223，2019.
[10] 侯罗玲，李硕凯.基于知识图谱、TF-IDF和BERT模型的冬奥知识问答系统[J].智能系统学报，2021，16（4）：819-826.
HOU L L，LI S K.Winter Olympic Q & A system based on knowledge map，TF-IDF and BERT model[J].CAAI Transactions on Intelligent Systems，2021，16（4）：819-826.
[11] SUN T，SHAO Y，QIU X，et al.CoLAKE：contextualized language and knowledge embedding[C]//Proceedings of the 28th International Conference on Computational Linguistics，2020.
[12] YAO L，MAO C S，LUO Y.KG-BERT：BERT for knowledge graph completion[J].arXiv：1909.03193，2019.
[13] LIU W J，ZHOU P.K-BERT：enabling language representation with knowledge graph[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020.
[14] 杨陟卓，韩晖，张虎，等.融合BERT语义表示的高考语文阅读理解问答研究[J].中文信息学报，2022，36（5）：59-66.
YANG Z Z，HAN H，ZHANG H，et al.BERT-based question answering of Gaokao Chinese reading comprehension[J].Journal of Chinese Information Processing，2022，36（5）：59-66.