基于表示学习的知识库问答研究进展与展望
面向知识库的问答（Question answering over knowledge base,KBQA）是问答系统的重要组成.近些年,随着以深度学习为代表的表示学习技术在多个领域的成功应用,许多研究者开始着手研究基于表示学习的知识库问答技术.其基本假设是把知识库问答看做是一个语义匹配的过程.通过表示学习知识库以及用户问题的语义表示,将知识库中的实体、关系以及问句文本转换为一个低维语义空间中的数值向量,在此基础上,利用数值计算,直接匹配与用户问句语义最相似的答案.从目前的结果看,基于表示学习的知识库问答系统在性能上已经超过传统知识库问答方法.本文将对现有基于表示学习的知识库问答的研究进展进行综...
Saved in:
| Published in | 自动化学报 Vol. 42; no. 6; pp. 807 - 818 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
中国科学院自动化研究所模式识别国家重点实验室 北京 100190
2016
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0254-4156 1874-1029 |
| DOI | 10.16383/j.aas.2016.c150674 |
Cover
| Abstract | 面向知识库的问答（Question answering over knowledge base,KBQA）是问答系统的重要组成.近些年,随着以深度学习为代表的表示学习技术在多个领域的成功应用,许多研究者开始着手研究基于表示学习的知识库问答技术.其基本假设是把知识库问答看做是一个语义匹配的过程.通过表示学习知识库以及用户问题的语义表示,将知识库中的实体、关系以及问句文本转换为一个低维语义空间中的数值向量,在此基础上,利用数值计算,直接匹配与用户问句语义最相似的答案.从目前的结果看,基于表示学习的知识库问答系统在性能上已经超过传统知识库问答方法.本文将对现有基于表示学习的知识库问答的研究进展进行综述,包括知识库表示学习和问句（文本）表示学习的代表性工作,同时对于其中存在难点以及仍存在的研究问题进行分析和讨论. |
|---|---|
| AbstractList | 面向知识库的问答(Question answering over knowledge base, KBQA)是问答系统的重要组成。近些年,随着以深度学习为代表的表示学习技术在多个领域的成功应用,许多研究者开始着手研究基于表示学习的知识库问答技术。其基本假设是把知识库问答看做是一个语义匹配的过程。通过表示学习知识库以及用户问题的语义表示,将知识库中的实体、关系以及问句文本转换为一个低维语义空间中的数值向量,在此基础上,利用数值计算,直接匹配与用户问句语义最相似的答案。从目前的结果看,基于表示学习的知识库问答系统在性能上已经超过传统知识库问答方法。本文将对现有基于表示学习的知识库问答的研究进展进行综述,包括知识库表示学习和问句(文本)表示学习的代表性工作,同时对于其中存在难点以及仍存在的研究问题进行分析和讨论。 面向知识库的问答（Question answering over knowledge base,KBQA）是问答系统的重要组成.近些年,随着以深度学习为代表的表示学习技术在多个领域的成功应用,许多研究者开始着手研究基于表示学习的知识库问答技术.其基本假设是把知识库问答看做是一个语义匹配的过程.通过表示学习知识库以及用户问题的语义表示,将知识库中的实体、关系以及问句文本转换为一个低维语义空间中的数值向量,在此基础上,利用数值计算,直接匹配与用户问句语义最相似的答案.从目前的结果看,基于表示学习的知识库问答系统在性能上已经超过传统知识库问答方法.本文将对现有基于表示学习的知识库问答的研究进展进行综述,包括知识库表示学习和问句（文本）表示学习的代表性工作,同时对于其中存在难点以及仍存在的研究问题进行分析和讨论. |
| Abstract_FL | Question answering over knowledge base (KBQA) is an important direction for the research of question answering. Recently, with the drastic development of deep learning, researchers and developers have paid more attentions to KBQA from this angle. They regarded this problem as a task of semantic matching. The semantics of knowledge base and users0 questions are learned through representation learning under the framework of deep learning. The entities and relations in knowledge base and the texts in questions could be represented as numerical vectors. Then, the answer could be figured out through similarity computation between the vectors of knowledge base and the vectors of the given question. From reported results, KBQA based on representation learning has obtained the best performance. This paper introduces the mainstream methods in this area. It further induces the typical approaches of representation learning on knowledge base and texts (questions), respectively. Finally, the current research challenges are discussed. |
| Author | 刘康 张元哲 纪国良 来斯惟 赵军 |
| AuthorAffiliation | 中国科学院自动化研究所模式识别国家重点实验室,北京100190 |
| AuthorAffiliation_xml | – name: 中国科学院自动化研究所模式识别国家重点实验室 北京 100190 |
| Author_FL | JI Guo-Liang ZHAO Jun LAI Si-Wei ZHANG Yuan-Zhe LIU Kang |
| Author_FL_xml | – sequence: 1 fullname: LIU Kang – sequence: 2 fullname: ZHANG Yuan-Zhe – sequence: 3 fullname: JI Guo-Liang – sequence: 4 fullname: LAI Si-Wei – sequence: 5 fullname: ZHAO Jun |
| Author_xml | – sequence: 1 fullname: 刘康 张元哲 纪国良 来斯惟 赵军 |
| BookMark | eNotjztLw1AYhg9SwVr7C9wc3BK_c86XcxmleIOCS_dwkia9oKk2iJdZHLtYEazQCio6VHERzeKfaUz9F0bq8r7Lw_PyLpJC1IkCQpYp2FRwxdfatjGxzYAK26cOCIlzpEiVRIsC0wVSBOaghdQRC6Qcxy0PqESpGYci0ekwmSS96d1Tdp-k48fJ5yi7Oc-GD9PXizS5_Ll-ycb9bNTPnt-nX4P07Wry0cvz-3awROZDsxcH5f8ukdrmRq2ybVV3t3Yq61XLdxSz0DHS4Qw1GE4RdRBoCRggUuULCNH3mOHceAhGGI514VPhcSXCEJknheYlsjrTHpsoNFHDbXeOulE-6J7Vmyfe32sQACwHV2ag3-xEjcNWjh50W_ume-oKoRlVVHH-Czqja8k |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2RA 92L CQIGP W92 ~WA 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.16383/j.aas.2016.c150674 |
| DatabaseName | 维普_期刊 中文科技期刊数据库-CALIS站点 维普中文期刊数据库 中文科技期刊数据库-工程技术 中文科技期刊数据库- 镜像站点 Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| DocumentTitleAlternate | Representation Learning for Question Answering over Knowledge Base：An Overview |
| DocumentTitle_FL | Representation Learning for Question Answering over Knowledge Base:An Overview |
| EISSN | 1874-1029 |
| EndPage | 818 |
| ExternalDocumentID | zdhxb201606002 669218183 |
| GrantInformation_xml | – fundername: 国家重点基础研究发展计划(973计划); 国家自然科学基金; “CCF-腾讯”犀牛鸟基金资助Supported by National Basic Research Program of China (973 Program); National Natural Science Founda-tion of China; CCF-Tencent Open Research Fund funderid: (2014CB340503); (61533018); (2014CB340503); (61533018); CCF-Tencent Open Research Fund |
| GroupedDBID | --K -0Y .~1 0R~ 1B1 1~. 1~5 2B. 2C0 2RA 4.4 457 4G. 5GY 5VS 5XA 5XJ 7-5 71M 8P~ 92H 92I 92L AAIKJ AALRI AAQFI AAXUO ACGFS ADEZE ADTZH AECPX AEKER AFTJW AGHFR AGYEJ AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS BLXMC CCEZO CQIGP CS3 CUBFJ CW9 EBS EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FNPLU GBLVA HVGLF HZ~ IHE J1W JJJVA M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SES TCJ TGT U1G U5S W92 ~WA 4A8 93N ABJNI ABWVN ACRPL ADNMO PSX |
| ID | FETCH-LOGICAL-c582-45a7532490a31449ee9704e4418c60f4cb2a33ab40a6a34d6c16b386ff42b7693 |
| ISSN | 0254-4156 |
| IngestDate | Thu May 29 04:10:30 EDT 2025 Wed Feb 14 10:18:14 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| Keywords | deep learning representation learning 深度学习 表示学习 Question answering over knowledge base (KBQA) semantic analysis 语义分析 知识库问答 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c582-45a7532490a31449ee9704e4418c60f4cb2a33ab40a6a34d6c16b386ff42b7693 |
| Notes | Question answering over knowledge base（KBQA）; deep learning; representation learning; semantic analysis Question answering over knowledge base（KBQA） is an important direction for the research of question answering. Recently, with the drastic development of deep learning, researchers and developers have paid more attentions to KBQA from this angle. They regarded this problem as a task of semantic matching. The semantics of knowledge base and users questions are learned through representation learning under the framework of deep learning. The entities and relations in knowledge base and the texts in questions could be represented as numerical vectors. Then, the answer could be figured out through similarity computation between the vectors of knowledge base and the vectors of the given question. From reported results, KBQA based on representation learning has obtained the best performance. This paper introduces the mainstream methods in this area. It further induces the typical approaches of representation learni |
| PageCount | 12 |
| ParticipantIDs | wanfang_journals_zdhxb201606002 chongqing_primary_669218183 |
| PublicationCentury | 2000 |
| PublicationDate | 2016 |
| PublicationDateYYYYMMDD | 2016-01-01 |
| PublicationDate_xml | – year: 2016 text: 2016 |
| PublicationDecade | 2010 |
| PublicationTitle | 自动化学报 |
| PublicationTitleAlternate | Acta Automatica Sinica |
| PublicationYear | 2016 |
| Publisher | 中国科学院自动化研究所模式识别国家重点实验室 北京 100190 |
| Publisher_xml | – name: 中国科学院自动化研究所模式识别国家重点实验室 北京 100190 |
| SSID | ssib017479230 ssib001102911 ssib006576350 ssib051375349 ssib007293330 ssj0059721 ssib007290157 ssib023646446 ssib005904210 |
| Score | 2.1528392 |
| Snippet | 面向知识库的问答（Question answering over knowledge base,KBQA）是问答系统的重要组成.近些年,随着以深度学习为代表的表示学习技术在多个领域的成功应用,许多研究者开... 面向知识库的问答(Question answering over knowledge base, KBQA)是问答系统的重要组成。近些年,随着以深度学习为代表的表示学习技术在多个领域的成功应用,许多研究者开始... |
| SourceID | wanfang chongqing |
| SourceType | Aggregation Database Publisher |
| StartPage | 807 |
| SubjectTerms | 深度学习 知识库问答 表示学习 语义分析 |
| Title | 基于表示学习的知识库问答研究进展与展望 |
| URI | http://lib.cqvip.com/qk/90250X/201606/669218183.html https://d.wanfangdata.com.cn/periodical/zdhxb201606002 |
| Volume | 42 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier) customDbUrl: eissn: 1874-1029 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0059721 issn: 0254-4156 databaseCode: GBLVA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3LbhMx0ArpBQ6Ipyjl0QM-RVt214-1j7vJhgoBp4B6i3Y32eaU8kgllDPi2AtFSBSpRQIEh4K4IMiFn0lI-xfMeN10RRECpJVle2fsGc9mPGPHY0KucZh0PJZJp5vzwOFc5E4KhoeTald3cNtImKA-t-_I5bv85opYqVT2S_9aWh-kS9nwt-dK_keqUAdyxVOy_yDZWaNQAXmQL6QgYUj_SsY0FlQ3aRTSmGOqYhorGno0VDQOaGgqASZs0FAaGE1DF19pAOYm06ShMFhNqiQCA4pmNNZUQwuxaadBtQEGXJvRNJKIFTWpjgyWR7UwXShDxqxGUl0HmLIRjIgKGjG0qdBQCxkAkyVqpXklDr4IA6KoVpbGKKiZXN1wBO_gYWZAGI38GlIJUEUfQGLUML0C_82aIaph-JbYJ7COvTEYjJphSuCDbcoDyu26SHFg0ypOcHoddEyLOa5Q7CrgMOXY1RWr-blf-sLLalwVN_EeWATFDHFksgHVxcxskyQY-N2TSxnGayxuHfolireUGo0pxY6ROT8Ao6hK5m5Et-6Fh7YrUldStkKDPi3ZZlJg7MDDcoA74KUtaygzdugLgqeJoSFnZbwoQJZ8f-Ex8FTR9y7MFoFhnMyCpB08G6ILmbx-lEUMRdJb668-AAPLnHfr50l_tWSatU6Rk9anWgyLH8hpUhn2zpATpUibZ4mebI_Go4291--nb0aT3XfjbzvTl0-m22_3Pj2djJ7tv_g43d2c7mxOP3zZ-741-fx8_HUD0h-vts6RVjNu1Zcde2uIkwnwFrlIgC-fazdhHue629WBy7tg9atMujnPUj9hLEm5m8iE8Y7MPJkyJfOc-yleDHqeVPtr_e4Fshj4LM86SQqVPheBTngg0g7PvA44AaD65snCbAza94vgMO2ZoOfJVTsqbasyHrWHnd7jFIfRxe3wi3_EXyDHEbJY7rtEqoOH693LYAAP0iv20_kJKa6F9g |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E7%9A%84%E7%9F%A5%E8%AF%86%E5%BA%93%E9%97%AE%E7%AD%94%E7%A0%94%E7%A9%B6%E8%BF%9B%E5%B1%95%E4%B8%8E%E5%B1%95%E6%9C%9B&rft.jtitle=%E8%87%AA%E5%8A%A8%E5%8C%96%E5%AD%A6%E6%8A%A5&rft.au=%E5%88%98%E5%BA%B7+%E5%BC%A0%E5%85%83%E5%93%B2+%E7%BA%AA%E5%9B%BD%E8%89%AF+%E6%9D%A5%E6%96%AF%E6%83%9F+%E8%B5%B5%E5%86%9B&rft.date=2016&rft.issn=0254-4156&rft.eissn=1874-1029&rft.volume=42&rft.issue=6&rft.spage=807&rft.epage=818&rft_id=info:doi/10.16383%2Fj.aas.2016.c150674&rft.externalDocID=669218183 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fimage.cqvip.com%2Fvip1000%2Fqk%2F90250X%2F90250X.jpg http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fzdhxb%2Fzdhxb.jpg |