知识与句法融合的因果关系抽取网络
因果关系抽取作为关系抽取的一个重要任务，近年来得到了广泛关注。现有的因果关系抽取方法大多将句法结构和背景知识割裂开进行研究，早期的因果关系抽取方法偏重于从句法结构层面进行分析，随着深度学习技术的发展，预训练模型结合背景知识的方法成为主流。然而上述两种方法均未完全融合句内信息和外部知识，带来了不同程度的信息缺失。为了解决这一问题，提出了结合句法结构和背景知识的因果关系抽取模型。该模型将句子解析为同时包含句法和知识的知识句法图结构，使用图卷积网络进行信息融合。模型同时考虑了句法和知识两部分信息，从而进一步丰富了实体嵌入，达到了良好的因果关系抽取效果。本模型在EventStoryLine数据集上取得...
Saved in:
| Published in | 大数据 Vol. 10; no. 3; pp. 82 - 92 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
人民邮电出版社有限公司
15.05.2024
同济大学电子与信息工程学院,上海 200000 China InfoCom Media Group |
| Subjects | |
| Online Access | Get full text |
| ISSN | 2096-0271 |
| DOI | 10.11959/j.issn.2096-0271.2024008 |
Cover
| Abstract | 因果关系抽取作为关系抽取的一个重要任务，近年来得到了广泛关注。现有的因果关系抽取方法大多将句法结构和背景知识割裂开进行研究，早期的因果关系抽取方法偏重于从句法结构层面进行分析，随着深度学习技术的发展，预训练模型结合背景知识的方法成为主流。然而上述两种方法均未完全融合句内信息和外部知识，带来了不同程度的信息缺失。为了解决这一问题，提出了结合句法结构和背景知识的因果关系抽取模型。该模型将句子解析为同时包含句法和知识的知识句法图结构，使用图卷积网络进行信息融合。模型同时考虑了句法和知识两部分信息，从而进一步丰富了实体嵌入，达到了良好的因果关系抽取效果。本模型在EventStoryLine数据集上取得了良好效果，F1值达到0.445，与现有方法相比提高了2.3%。 |
|---|---|
| AbstractList | 因果关系抽取作为关系抽取的一个重要任务，近年来得到了广泛关注。现有的因果关系抽取方法大多将句法结构和背景知识割裂开进行研究，早期的因果关系抽取方法偏重于从句法结构层面进行分析，随着深度学习技术的发展，预训练模型结合背景知识的方法成为主流。然而上述两种方法均未完全融合句内信息和外部知识，带来了不同程度的信息缺失。为了解决这一问题，提出了结合句法结构和背景知识的因果关系抽取模型。该模型将句子解析为同时包含句法和知识的知识句法图结构，使用图卷积网络进行信息融合。模型同时考虑了句法和知识两部分信息，从而进一步丰富了实体嵌入，达到了良好的因果关系抽取效果。本模型在EventStoryLine数据集上取得了良好效果，F1值达到0.445，与现有方法相比提高了2.3%。 TP391.1; 因果关系抽取作为关系抽取的一个重要任务,近年来得到了广泛关注.现有的因果关系抽取方法大多将句法结构和背景知识割裂开进行研究,早期的因果关系抽取方法偏重于从句法结构层面进行分析,随着深度学习技术的发展,预训练模型结合背景知识的方法成为主流.然而上述两种方法均未完全融合句内信息和外部知识,带来了不同程度的信息缺失.为了解决这一问题,提出了结合句法结构和背景知识的因果关系抽取模型.该模型将句子解析为同时包含句法和知识的知识句法图结构,使用图卷积网络进行信息融合.模型同时考虑了句法和知识两部分信息,从而进一步丰富了实体嵌入,达到了良好的因果关系抽取效果.本模型在EventStoryLine数据集上取得了良好效果,F1值达到0.445,与现有方法相比提高了2.3％. |
| Abstract_FL | Event causality identification is an important task of relationship extraction, which has received much attention recent years. Most of the existing methods separate syntactic structure from the background knowledge information. The early causality extraction methods focus on the analysis of syntactic structure level. With the development of deep learning, the methods that use the pre-training model combined with background knowledge has become the mainstream. However, neither of the above two kinds of methods fully integrates the sentence information and external knowledge, resulting in different degrees of information loss. To address this problem, we proposed a novel model of event causality identification combining syntactic structure and background knowledge. Our model parses sentences into knowledge syntactic graph structures that contain both syntax and knowledge, and uses the graph convolution network for information fusion. It considers both syntax and knowledge information, which further enriches the event representation and performs effectively. In experiments on the widely-used dataset EventStoryLine, the F1 score of our model achieves 0.445, a 2.3％ improvement over existing methods. |
| Author | 丁玲 向阳 汪诗蕊 陈建廷 解博涵 |
| AuthorAffiliation | 同济大学电子与信息工程学院,上海 200000 |
| AuthorAffiliation_xml | – name: 同济大学电子与信息工程学院,上海 200000 |
| Author_FL | DING Ling XIANG Yang XIE Bohan WANG Shirui CHEN Jianting |
| Author_FL_xml | – sequence: 1 fullname: WANG Shirui – sequence: 2 fullname: XIE Bohan – sequence: 3 fullname: DING Ling – sequence: 4 fullname: CHEN Jianting – sequence: 5 fullname: XIANG Yang |
| Author_xml | – sequence: 1 fullname: 汪诗蕊 organization: 同济大学电子与信息工程学院,上海200000 – sequence: 2 fullname: 解博涵 organization: 同济大学电子与信息工程学院,上海200000 – sequence: 3 fullname: 丁玲 organization: 同济大学电子与信息工程学院,上海200000 – sequence: 4 fullname: 陈建廷 organization: 同济大学电子与信息工程学院,上海200000 – sequence: 5 fullname: 向阳 organization: 同济大学电子与信息工程学院,上海200000 |
| BookMark | eNo9kLtKA0EYhaeIYIx5BcHCcuNcdmdnS4m3SMBCrYe57IZd4q7sKGKvIoJGCy00RJvUFmmEkLdxs3kMh0Ss_sPh8P2HswIqaZaGAKwj2EAo8ILNpBEbkzYwDKgDsY-swi6ErAKq_94yqBsTS0ioSyijpApg-TGcfd3-fD8WveF09DIbPBRPd-XbdfH-OR30i5tRORpP7ydF77WcPJfj_ipYikTXhPW_WwMnuzvHzX2nfbjXam61HWXrMCdExL7A0BMyiDQLJHYJ8xnVxFOuJyPP1ZopQiGkxJUaiSjUWgeuF0oWQC8iNdBacHUmEn6Wx6civ-KZiPncyPIOF_l5rLoh11JL5SOMNFZuQEOmLd9XAistECbMsjYWrEuRRiLt8CS7yFPbnmthkvlOxC5lc2uLnBLG8NQYzbePDhY7zgO_Bzh7nQ |
| ClassificationCodes | TP391.1 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | NSCOK 2B. 4A8 92I 93N PSX TCJ DOA |
| DOI | 10.11959/j.issn.2096-0271.2024008 |
| DatabaseName | 国家哲学社会科学文献中心 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) DOAJ Directory of Open Access Journals |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitle_FL | Event causality identification network based on knowledge and syntactic structure |
| EndPage | 92 |
| ExternalDocumentID | oai_doaj_org_article_dbdbc7121d2c496e8dbf57ca2cda1238 dasj202403008 DSJ2024003008 |
| GroupedDBID | -0I -SI -S~ 2RA 5VR 92M 9D9 9DI AAXDM ALMA_UNASSIGNED_HOLDINGS CAJEI FA0 GROUPED_DOAJ JUIAU NSCOK NTYSC PB1 PB5 Q-- Q-8 R-I RT9 S.. T8Y U1F U5I ~NM ~NO 2B. 4A8 92I 93N AAITT AFUIB CQIGP PSX TCJ |
| ID | FETCH-LOGICAL-c1198-e13436205ab9fd89b2438786d35c45bf54dd8c3600634bd1afeddd945eb8905f3 |
| IEDL.DBID | DOA |
| ISSN | 2096-0271 |
| IngestDate | Tue Oct 14 18:50:39 EDT 2025 Thu May 29 03:56:13 EDT 2025 Tue Jan 21 20:55:07 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 3 |
| Keywords | 因果关系抽取 图卷积网络 自然语言处理 预训练模型 natural language processing event causality identification syntactic structure graph convolution network |
| Language | Chinese |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c1198-e13436205ab9fd89b2438786d35c45bf54dd8c3600634bd1afeddd945eb8905f3 |
| OpenAccessLink | https://doaj.org/article/dbdbc7121d2c496e8dbf57ca2cda1238 |
| PageCount | 11 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_dbdbc7121d2c496e8dbf57ca2cda1238 wanfang_journals_dasj202403008 cass_nssd_DSJ2024003008 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-05-15 |
| PublicationDateYYYYMMDD | 2024-05-15 |
| PublicationDate_xml | – month: 05 year: 2024 text: 2024-05-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | 大数据 |
| PublicationTitle_FL | Big Data Research |
| PublicationYear | 2024 |
| Publisher | 人民邮电出版社有限公司 同济大学电子与信息工程学院,上海 200000 China InfoCom Media Group |
| Publisher_xml | – name: 人民邮电出版社有限公司 – name: 同济大学电子与信息工程学院,上海 200000 – name: China InfoCom Media Group |
| SSID | ssib036436863 ssib024184013 ssib051371281 ssib057785240 ssib035218648 ssj0002857271 ssib058759006 |
| Score | 2.3839023 |
| Snippet | 因果关系抽取作为关系抽取的一个重要任务，近年来得到了广泛关注。现有的因果关系抽取方法大多将句法结构和背景知识割裂开进行研究，早期的因果关系抽取方法偏重于从句法结... TP391.1; 因果关系抽取作为关系抽取的一个重要任务,近年来得到了广泛关注.现有的因果关系抽取方法大多将句法结构和背景知识割裂开进行研究,早期的因果关系抽取方法偏重于... |
| SourceID | doaj wanfang cass |
| SourceType | Open Website Aggregation Database |
| StartPage | 82 |
| SubjectTerms | 因果关系抽取 图卷积网络 自然语言处理 预训练模型 |
| Title | 知识与句法融合的因果关系抽取网络 |
| URI | https://www.ncpssd.cn/Literature/articleinfo?id=DSJ2024003008&type=journalArticle https://d.wanfangdata.com.cn/periodical/dasj202403008 https://doaj.org/article/dbdbc7121d2c496e8dbf57ca2cda1238 |
| Volume | 10 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals issn: 2096-0271 databaseCode: DOA dateStart: 20150101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: true ssIdentifier: ssj0002857271 providerName: Directory of Open Access Journals – providerCode: PRVEBS databaseName: EBSCOhost Academic Search Ultimate issn: 2096-0271 databaseCode: ABDBF dateStart: 20220301 customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn isFulltext: true dateEnd: 99991231 titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn omitProxy: true ssIdentifier: ssib035218648 providerName: EBSCOhost – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources issn: 2096-0271 databaseCode: M~E dateStart: 20150101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://road.issn.org omitProxy: true ssIdentifier: ssib058759006 providerName: ISSN International Centre |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV29b9QwFLdQkRALAvF1fJyKxBoaO3Zsjz3aU1WpLFCpW2T7OaAbAuLKwsAEqKpEWwYYoCosnRluQar635BL_wyenai9rUuXKImjvPg9-72fneefCXnsjSklUJ5Yl9qEewnoB5VNmADJtecYdMLUwNqzfGWdr26IjZmtvkJOWEsP3CpuASxYJymjwBzXuVdgSyGdYQ4Met24zDdVemYwhS0Jw5KaHTggyqAqPwP-WR6I18-IpwTNZPildHotpRKsY0EZxSkogYE-jN5YGrN2Jb1CHkWPo4VeGMUe--S0DM9CbqZCP-8QA3f7AcR1QVVpqpczIWx4nVzrsOf8YlvnG-TS-1c3Sdr8Ojz58_nf351693A6-XZy8KXe22p-fKx__p4e7NefJs3kaLp9XO9-b46_Nkf7t8j6cPnF05Wk20Yhcfh1KvE0w9qyVBirS1DaMp4pqXLIhOMCtckBlMvygFa4BWpKDwCaC2-VTkWZ3SZz1evK3yXzzgnD0eheqMAzoyw3iGcUPstkiWU9cifUt6jGYyiWnq-2ashQEz0yCCoo3rQcGkVgtY430NZFZ-viPFv3SL9TYNH1tHEBZjyKYoKUexch5T65Gl4YUgSoeEDmNt--8w8ReWzaPrm8OFgaDPuxseFx7cPyf3C23Mk |
| linkProvider | Directory of Open Access Journals |
| 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=%E7%9F%A5%E8%AF%86%E4%B8%8E%E5%8F%A5%E6%B3%95%E8%9E%8D%E5%90%88%E7%9A%84%E5%9B%A0%E6%9E%9C%E5%85%B3%E7%B3%BB%E6%8A%BD%E5%8F%96%E7%BD%91%E7%BB%9C&rft.jtitle=%E5%A4%A7%E6%95%B0%E6%8D%AE&rft.au=%E6%B1%AA%E8%AF%97%E8%95%8A&rft.au=%E8%A7%A3%E5%8D%9A%E6%B6%B5&rft.au=%E4%B8%81%E7%8E%B2&rft.au=%E9%99%88%E5%BB%BA%E5%BB%B7&rft.date=2024-05-15&rft.pub=%E4%BA%BA%E6%B0%91%E9%82%AE%E7%94%B5%E5%87%BA%E7%89%88%E7%A4%BE%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8&rft.issn=2096-0271&rft.volume=10&rft.issue=3&rft.spage=82&rft.epage=92&rft_id=info:doi/10.11959%2Fj.issn.2096-0271.2024008&rft.externalDocID=DSJ2024003008 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fdasj%2Fdasj.jpg |