CodeKGC: Code Language Model for Generative Knowledge Graph Construction
Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specification language. However, large generative language model trained on structured data such as code has demonstrated impressiv...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
18.01.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specification language. However, large generative language model trained on structured data such as code has demonstrated impressive capability in understanding natural language for structural prediction and reasoning tasks. Intuitively, we address the task of generative knowledge graph construction with code language model: given a code-format natural language input, the target is to generate triples which can be represented as code completion tasks. Specifically, we develop schema-aware prompts that effectively utilize the semantic structure within the knowledge graph. As code inherently possesses structure, such as class and function definitions, it serves as a useful model for prior semantic structural knowledge. Furthermore, we employ a rationale-enhanced generation method to boost the performance. Rationales provide intermediate steps, thereby improving knowledge extraction abilities. Experimental results indicate that the proposed approach can obtain better performance on benchmark datasets compared with baselines. Code and datasets are available in https://github.com/zjunlp/DeepKE/tree/main/example/llm. |
---|---|
AbstractList | Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specification language. However, large generative language model trained on structured data such as code has demonstrated impressive capability in understanding natural language for structural prediction and reasoning tasks. Intuitively, we address the task of generative knowledge graph construction with code language model: given a code-format natural language input, the target is to generate triples which can be represented as code completion tasks. Specifically, we develop schema-aware prompts that effectively utilize the semantic structure within the knowledge graph. As code inherently possesses structure, such as class and function definitions, it serves as a useful model for prior semantic structural knowledge. Furthermore, we employ a rationale-enhanced generation method to boost the performance. Rationales provide intermediate steps, thereby improving knowledge extraction abilities. Experimental results indicate that the proposed approach can obtain better performance on benchmark datasets compared with baselines. Code and datasets are available in https://github.com/zjunlp/DeepKE/tree/main/example/llm. |
Author | Guo, Wei Xiong, Feiyu Jiang, Yinuo Zhang, Ningyu Bi, Zhen Chen, Jing Chen, Huajun |
Author_xml | – sequence: 1 givenname: Zhen surname: Bi fullname: Bi, Zhen – sequence: 2 givenname: Jing surname: Chen fullname: Chen, Jing – sequence: 3 givenname: Yinuo surname: Jiang fullname: Jiang, Yinuo – sequence: 4 givenname: Feiyu surname: Xiong fullname: Xiong, Feiyu – sequence: 5 givenname: Wei surname: Guo fullname: Guo, Wei – sequence: 6 givenname: Huajun surname: Chen fullname: Chen, Huajun – sequence: 7 givenname: Ningyu surname: Zhang fullname: Zhang, Ningyu |
BookMark | eNqNi80KgkAUhYcoyMp3GGgtjDNZ1lZKwdy1lyGvpsgdm596_SboAVqd7_CdsyJzVAgzEnAh4ijdcb4koTEDY4zvDzxJRECKTDVQ5tmJfoFeJXZOdkAr30baKk1zQNDS9i-gJar3CI3XuZbTw1_QWO3utle4IYtWjgbCX67J9nK-ZUU0afV0YGw9KKfRq5qnTLBjwkQs_lt9AAOXPNE |
ContentType | Paper |
Copyright | 2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_28030950313 |
IEDL.DBID | BENPR |
IngestDate | Thu Oct 10 17:02:15 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_28030950313 |
OpenAccessLink | https://www.proquest.com/docview/2803095031?pq-origsite=%requestingapplication% |
PQID | 2803095031 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2803095031 |
PublicationCentury | 2000 |
PublicationDate | 20240118 |
PublicationDateYYYYMMDD | 2024-01-18 |
PublicationDate_xml | – month: 01 year: 2024 text: 20240118 day: 18 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2024 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.5226483 |
SecondaryResourceType | preprint |
Snippet | Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Datasets Knowledge Knowledge representation Language Natural language Natural language processing Semantics Specification and description languages Structured data |
Title | CodeKGC: Code Language Model for Generative Knowledge Graph Construction |
URI | https://www.proquest.com/docview/2803095031 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LSwMxEB5sF8GbT3zUEtBrsPtIN_UiuOwDa0sRhd5KdjM9iW1dz_3tzqxZPQi9JQTyYjIz-SaZD-DWRiQYJlYSB8tQckIuqS2WdNzJVqJSlTL8UXgyHRZv0dNczR3gVrtnla1ObBS1XVWMkd8xixK5AySDD-uNZNYojq46Co0OeIEfcZjWe0yns5dflCUYxuQzh_8UbWM9skPwZmaNn0ewhx_HsN88uqzqEyiSlcVxntwLLohnBx0K5id7F-RNip-k0KyRxLgFv0TOOaYFM222uV9P4SZLX5NCtsMvnIjUi78FhWfQpbs-noMwhq4juDR6RK6U9mMzsBUaVYYYq8hEeAG9XT1d7m6-goOAbDIjCL7uQZdmiddkU7_KPnR0lvfd9lFtsk2_AYDsgPY |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED-0RfTNT_yYGtDX4LY2a_RFsGyrtitDJuytpM3tabhp_f_xrqb6IOwtEMgXl7vLL8nvB3BrQzIMEymJ3UUgmZBLaoslbXeKlahUpQx_FJ7kg-QtfJmruQPcavessvWJjaO2q4ox8jtWUaJ0gGzwcf0hWTWKb1edhMY2-Ey5qT3wn4b59PUXZekPIsqZg3-Otokeo33wp2aNnwewhe-HsNM8uqzqI0jilcV0HD8ILojMQYeC9cmWgrJJ8UMKzR5JpC34JcbMMS1YabPlfj2Gm9FwFiey7b5wJlIXfxMKTsCjsz6egjCGjiO4MPqeUindi0zXVmhUGWCkQhPiGXQ2tXS-ufoadpPZJCuy5zy9gL0-xWdGE3q6Ax6NGC8pvn6VV24RvwGnw4HV |
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=CodeKGC%3A+Code+Language+Model+for+Generative+Knowledge+Graph+Construction&rft.jtitle=arXiv.org&rft.au=Bi%2C+Zhen&rft.au=Chen%2C+Jing&rft.au=Jiang%2C+Yinuo&rft.au=Xiong%2C+Feiyu&rft.date=2024-01-18&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |