面向知识库问答的问句语义解析研究综述
A Survey of Question Semantic Parsing for Knowledge Base Question Answering
查看参考文献123篇
|
文摘
|
知识库问答(Knowledge Base Question Answering,KBQA)借助知识库中精度高、关联性强的结构化知识,为给定的复杂事实型问句提供准确、简短的答案.语义解析是知识库问答的主流方法之一,该类方法在给定的问句语义表征形式下,将非结构化的问句映射为结构化的语义表征,再将其改写为知识库查询获取答案.目前,面向知识库问答的语义解析方法主要面临三个挑战:首先是如何选择合适的语义表征形式以表达问句的语义,然后是如何解析问句的复杂语义并输出相应的语义表征,最后是如何应对特定领域中数据标注成本高昂、高质量数据匮乏的问题.本文从上述挑战出发,分析了知识库问答中常用的语义表征的特点与不足,然后梳理现有方法并总结分析其如何应对问句的复杂语义,接着介绍了当前方法在标注数据匮乏的低资源场景下的尝试,最后展望并讨论了面向知识库问答的语义解析的未来发展方向. |
|
其他语种文摘
|
Knowledge base question answering(KBQA) provides accurate and short answers to complex factoid questions with the help of high-precision and highly relevant structured knowledge in the knowledge base(KB). Semantic parsing has become one of the mainstream methods of KBQA. Under the given form of question meaning representation, this kind of method maps unstructured questions into structured meaning representations, and then rewrites them as KB queries to obtain answers. At present, semantic parsing for KBQA mainly faces three challenges: first how to choose a suitable meaning representation form to express the semantics of questions, then how to parse the complex semantics of questions and output the corresponding meaning representations, and finally how to deal with the high cost of labeling datasets and the lack of annotated data in specific domains. Starting from the above challenges, this paper first analyzed the characteristics and shortcomings of meaning representations commonly used in KBQA and then combed out how existing methods deal with the complex semantics of questions. After that, this paper introduced the current attempts in low-resource scenarios and finally discussed the future directions of semantic parsing for KBQA. |
|
来源
|
电子学报
,2022,50(9):2242-2264 【核心库】
|
|
DOI
|
10.12263/DZXB.20220212
|
|
关键词
|
知识库
;
问答
;
语义表征
;
语义解析
;
低资源
|
|
地址
|
1.
中国科学院计算技术研究所数据智能系统研究中心, 北京, 100190
2.
中国科学院大学计算机科学与技术学院, 北京, 101408
3.
中科大数据研究院, 河南, 郑州, 450046
4.
中国科学院计算技术研究所, 中国科学院网络数据科学与技术重点实验室, 北京, 100190
|
|
语种
|
中文 |
|
文献类型
|
综述型 |
|
ISSN
|
0372-2112 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金
;
中原英才计划-中原科技创新领军人才项目资助
|
|
文献收藏号
|
CSCD:7323075
|
参考文献 共
123
共7页
|
|
1.
Zettlemoyer L S. Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars.
Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence,2005:658-666
|
CSCD被引
1
次
|
|
|
|
|
2.
Berant J. Semantic parsing on freebase from question-answer pairs.
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing,2013:1533-1544
|
CSCD被引
25
次
|
|
|
|
|
3.
Yih W T. Semantic parsing via staged query graph generation: Question answering with knowledge base.
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing,2015:1321-1331
|
CSCD被引
16
次
|
|
|
|
|
4.
Bordes A. Question answering with subgraph embeddings.
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP),2014:615-620
|
CSCD被引
3
次
|
|
|
|
|
5.
Dong L. Question answering over freebase with multi-column convolutional neural networks.
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing,2015:260-269
|
CSCD被引
26
次
|
|
|
|
|
6.
Miller A. Key-value memory networks for directly reading documents.
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing,2016:1400-1409
|
CSCD被引
9
次
|
|
|
|
|
7.
Green B F. Baseball: An automatic question-answerer.
IRE-AIEE-ACM'61 (Western): western joint IRE-AIEE-ACM computer conference,1961:219-224
|
CSCD被引
1
次
|
|
|
|
|
8.
Hoffner K. Survey on challenges of question answering in the semantic web.
Semantic Web,2017,8(6):895-920
|
CSCD被引
2
次
|
|
|
|
|
9.
Diefenbach D. Core techniques of question answering systems over knowledge bases: A survey.
Knowledge and Information Systems,2018,55(3):529-569
|
CSCD被引
24
次
|
|
|
|
|
10.
Wu P Y. A survey of question answering over knowledge base.
China Conference on Knowledge Graph and Semantic Computing,2019:86-97
|
CSCD被引
2
次
|
|
|
|
|
11.
Lan Y S. A survey on complex knowledge base question answering: Methods, challenges and solutions.
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence: Survey Track. International Joint Conferences on Artificial Intelligence Organization,2021:4483-4491
|
CSCD被引
1
次
|
|
|
|
|
12.
Miller G A. WordNet: A lexical database for English.
Communications of the ACM,1995,38(11):39-41
|
CSCD被引
314
次
|
|
|
|
|
13.
Auer S. DBpedia: A Nucleus for a Web of Open Data.
The Semantic Web,2007:722-735
|
CSCD被引
51
次
|
|
|
|
|
14.
Bollacker K. Freebase: A collaboratively created graph database for structuring human knowledge.
Proceedings of the 2008 ACM SIGMOD international conference on Management of data,2008:1247-1250
|
CSCD被引
103
次
|
|
|
|
|
15.
Vrandecic D. Wikidata: A free collaborative knowledgebase.
Communications of the ACM,2014,57(10):78-85
|
CSCD被引
113
次
|
|
|
|
|
16.
Church A. A set of postulates for the foundation of logic.
The Annals of Mathematics,1932,33(2):346-366
|
CSCD被引
4
次
|
|
|
|
|
17.
Carpenter B.
Type-logical Semantics,1997
|
CSCD被引
1
次
|
|
|
|
|
18.
Harris S. SPARQL 1.1 query language.
W3C recommendation,2013,21(10):778
|
CSCD被引
3
次
|
|
|
|
|
19.
Xu K. Question answering on freebase via relation extraction and textual evidence.
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics,2016:2326-2336
|
CSCD被引
7
次
|
|
|
|
|
20.
Hao Y C. An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge.
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics,2017:221-231
|
CSCD被引
4
次
|
|
|
|
|
了解气象卫星更多信息，请访问