Academic Journal
Leveraging Concept-Enhanced Pre-Training Model and Masked-Entity Language Model for Named Entity Disambiguation
| العنوان: | Leveraging Concept-Enhanced Pre-Training Model and Masked-Entity Language Model for Named Entity Disambiguation |
|---|---|
| المؤلفون: | Zizheng Ji, Lin Dai, Jin Pang, Tingting Shen |
| المصدر: | IEEE Access, Vol 8, Pp 100469-100484 (2020) |
| بيانات النشر: | IEEE, 2020. |
| سنة النشر: | 2020 |
| المجموعة: | LCC:Electrical engineering. Electronics. Nuclear engineering |
| مصطلحات موضوعية: | Named entity disambiguation, pre-training, lexical knowledge, Electrical engineering. Electronics. Nuclear engineering, TK1-9971 |
| الوصف: | Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity mentions in an input-text sequence to their correct references in a knowledge graph. We tackle NED problem by leveraging two novel objectives for pre-training framework, and propose a novel pre-training NED model. Especially, the proposed pre-training NED model consists of: (i) concept-enhanced pre-training, aiming at identifying valid lexical semantic relations with the concept semantic constraints derived from external resource Probase; and (ii) masked entity language model, aiming to train the contextualized embedding by predicting randomly masked entities based on words and non-masked entities in the given input-text. Therefore, the proposed pre-training NED model could merge the advantage of pre-training mechanism for generating contextualized embedding with the superiority of the lexical knowledge (e.g., concept knowledge emphasized here) for understanding language semantic. We conduct experiments on the CoNLL dataset and TAC dataset, and various datasets provided by GERBIL platform. The experimental results demonstrate that the proposed model achieves significantly higher performance than previous models. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2169-3536 |
| Relation: | https://ieeexplore.ieee.org/document/9091850/; https://doaj.org/toc/2169-3536 |
| DOI: | 10.1109/ACCESS.2020.2994247 |
| URL الوصول: | https://doaj.org/article/176fbfa4ba0845e99129abc4f7c98e97 |
| رقم الانضمام: | edsdoj.176fbfa4ba0845e99129abc4f7c98e97 |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | ResultId |
1 |
|---|---|
| Header |
edsdoj Directory of Open Access Journals edsdoj.176fbfa4ba0845e99129abc4f7c98e97 930 3 Academic Journal academicJournal 930.017944335938 |
| PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsdoj&AN=edsdoj.176fbfa4ba0845e99129abc4f7c98e97&custid=s6537998&authtype=sso |
| FullText |
Array
(
[Availability] => 0
)
Array ( [0] => Array ( [Url] => https://doaj.org/article/176fbfa4ba0845e99129abc4f7c98e97 [Name] => EDS - DOAJ [Category] => fullText [Text] => View record in DOAJ [MouseOverText] => View record in DOAJ ) [1] => Array ( [Url] => https://resolver.ebscohost.com/openurl?custid=s6537998&groupid=main&authtype=ip,guest&sid=EBSCO:edsdoj&genre=article&issn=21693536&ISBN=&volume=8&issue=&date=20200101&spage=100469&pages=100469-100484&title=IEEE Access&atitle=Leveraging%20Concept-Enhanced%20Pre-Training%20Model%20and%20Masked-Entity%20Language%20Model%20for%20Named%20Entity%20Disambiguation&id=DOI:10.1109/ACCESS.2020.2994247 [Name] => Full Text Finder (s6537998api) [Category] => fullText [Text] => Full Text Finder [Icon] => https://imageserver.ebscohost.com/branding/images/FTF.gif [MouseOverText] => Full Text Finder ) ) |
| Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => Leveraging Concept-Enhanced Pre-Training Model and Masked-Entity Language Model for Named Entity Disambiguation
)
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Zizheng+Ji%22">Zizheng Ji</searchLink><br /><searchLink fieldCode="AR" term="%22Lin+Dai%22">Lin Dai</searchLink><br /><searchLink fieldCode="AR" term="%22Jin+Pang%22">Jin Pang</searchLink><br /><searchLink fieldCode="AR" term="%22Tingting+Shen%22">Tingting Shen</searchLink> ) Array ( [Name] => TitleSource [Label] => Source [Group] => Src [Data] => IEEE Access, Vol 8, Pp 100469-100484 (2020) ) Array ( [Name] => Publisher [Label] => Publisher Information [Group] => PubInfo [Data] => IEEE, 2020. ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2020 ) Array ( [Name] => Subset [Label] => Collection [Group] => HoldingsInfo [Data] => LCC:Electrical engineering. Electronics. Nuclear engineering ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22Named+entity+disambiguation%22">Named entity disambiguation</searchLink><br /><searchLink fieldCode="DE" term="%22pre-training%22">pre-training</searchLink><br /><searchLink fieldCode="DE" term="%22lexical+knowledge%22">lexical knowledge</searchLink><br /><searchLink fieldCode="DE" term="%22Electrical+engineering%2E+Electronics%2E+Nuclear+engineering%22">Electrical engineering. Electronics. Nuclear engineering</searchLink><br /><searchLink fieldCode="DE" term="%22TK1-9971%22">TK1-9971</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity mentions in an input-text sequence to their correct references in a knowledge graph. We tackle NED problem by leveraging two novel objectives for pre-training framework, and propose a novel pre-training NED model. Especially, the proposed pre-training NED model consists of: (i) concept-enhanced pre-training, aiming at identifying valid lexical semantic relations with the concept semantic constraints derived from external resource Probase; and (ii) masked entity language model, aiming to train the contextualized embedding by predicting randomly masked entities based on words and non-masked entities in the given input-text. Therefore, the proposed pre-training NED model could merge the advantage of pre-training mechanism for generating contextualized embedding with the superiority of the lexical knowledge (e.g., concept knowledge emphasized here) for understanding language semantic. We conduct experiments on the CoNLL dataset and TAC dataset, and various datasets provided by GERBIL platform. The experimental results demonstrate that the proposed model achieves significantly higher performance than previous models. ) Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => article ) Array ( [Name] => Format [Label] => File Description [Group] => SrcInfo [Data] => electronic resource ) Array ( [Name] => Language [Label] => Language [Group] => Lang [Data] => English ) Array ( [Name] => ISSN [Label] => ISSN [Group] => ISSN [Data] => 2169-3536 ) Array ( [Name] => NoteTitleSource [Label] => Relation [Group] => SrcInfo [Data] => https://ieeexplore.ieee.org/document/9091850/; https://doaj.org/toc/2169-3536 ) Array ( [Name] => DOI [Label] => DOI [Group] => ID [Data] => 10.1109/ACCESS.2020.2994247 ) Array ( [Name] => URL [Label] => Access URL [Group] => URL [Data] => <link linkTarget="URL" linkTerm="https://doaj.org/article/176fbfa4ba0845e99129abc4f7c98e97" linkWindow="_blank">https://doaj.org/article/176fbfa4ba0845e99129abc4f7c98e97</link> ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsdoj.176fbfa4ba0845e99129abc4f7c98e97 ) |
| RecordInfo |
Array
(
[BibEntity] => Array
(
[Identifiers] => Array
(
[0] => Array
(
[Type] => doi
[Value] => 10.1109/ACCESS.2020.2994247
)
)
[Languages] => Array
(
[0] => Array
(
[Text] => English
)
)
[PhysicalDescription] => Array
(
[Pagination] => Array
(
[PageCount] => 16
[StartPage] => 100469
)
)
[Subjects] => Array
(
[0] => Array
(
[SubjectFull] => Named entity disambiguation
[Type] => general
)
[1] => Array
(
[SubjectFull] => pre-training
[Type] => general
)
[2] => Array
(
[SubjectFull] => lexical knowledge
[Type] => general
)
[3] => Array
(
[SubjectFull] => Electrical engineering. Electronics. Nuclear engineering
[Type] => general
)
[4] => Array
(
[SubjectFull] => TK1-9971
[Type] => general
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Leveraging Concept-Enhanced Pre-Training Model and Masked-Entity Language Model for Named Entity Disambiguation
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Zizheng Ji
)
)
)
[1] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Lin Dai
)
)
)
[2] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Jin Pang
)
)
)
[3] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Tingting Shen
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 01
[M] => 01
[Type] => published
[Y] => 2020
)
)
[Identifiers] => Array
(
[0] => Array
(
[Type] => issn-print
[Value] => 21693536
)
)
[Numbering] => Array
(
[0] => Array
(
[Type] => volume
[Value] => 8
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => IEEE Access
[Type] => main
)
)
)
)
)
)
)
|
| IllustrationInfo |