DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG
| Title: | DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG |
|---|---|
| Authors: | Kim, Jinyoung, Ko, Dayoon, Kim, Gunhee |
| Publication Year: | 2024 |
| Collection: | Computer Science |
| Subject Terms: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
| More Details: | In the rapidly evolving landscape of language, resolving new linguistic expressions in continuously updating knowledge bases remains a formidable challenge. This challenge becomes critical in retrieval-augmented generation (RAG) with knowledge bases, as emerging expressions hinder the retrieval of relevant documents, leading to generator hallucinations. To address this issue, we introduce a novel task aimed at resolving emerging mentions to dynamic entities and present DynamicER benchmark. Our benchmark includes dynamic entity mention resolution and entity-centric knowledge-intensive QA task, evaluating entity linking and RAG model's adaptability to new expressions, respectively. We discovered that current entity linking models struggle to link these new expressions to entities. Therefore, we propose a temporal segmented clustering method with continual adaptation, effectively managing the temporal dynamics of evolving entities and emerging mentions. Extensive experiments demonstrate that our method outperforms existing baselines, enhancing RAG model performance on QA task with resolved mentions. Comment: EMNLP 2024 Main |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2410.11494 |
| Accession Number: | edsarx.2410.11494 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2410.11494 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20241015&spage=&pages=&title=DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG&atitle=DynamicER%3A%20Resolving%20Emerging%20Mentions%20to%20Dynamic%20Entities%20for%20RAG&aulast=Kim%2C%20Jinyoung&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2410.11494 RelevancyScore: 1112 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1112.2705078125 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Kim%2C+Jinyoung%22">Kim, Jinyoung</searchLink><br /><searchLink fieldCode="AR" term="%22Ko%2C+Dayoon%22">Ko, Dayoon</searchLink><br /><searchLink fieldCode="AR" term="%22Kim%2C+Gunhee%22">Kim, Gunhee</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computation+and+Language%22">Computer Science - Computation and Language</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Artificial+Intelligence%22">Computer Science - Artificial Intelligence</searchLink> – Name: Abstract Label: Description Group: Ab Data: In the rapidly evolving landscape of language, resolving new linguistic expressions in continuously updating knowledge bases remains a formidable challenge. This challenge becomes critical in retrieval-augmented generation (RAG) with knowledge bases, as emerging expressions hinder the retrieval of relevant documents, leading to generator hallucinations. To address this issue, we introduce a novel task aimed at resolving emerging mentions to dynamic entities and present DynamicER benchmark. Our benchmark includes dynamic entity mention resolution and entity-centric knowledge-intensive QA task, evaluating entity linking and RAG model's adaptability to new expressions, respectively. We discovered that current entity linking models struggle to link these new expressions to entities. Therefore, we propose a temporal segmented clustering method with continual adaptation, effectively managing the temporal dynamics of evolving entities and emerging mentions. Extensive experiments demonstrate that our method outperforms existing baselines, enhancing RAG model performance on QA task with resolved mentions.<br />Comment: EMNLP 2024 Main – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2410.11494" linkWindow="_blank">http://arxiv.org/abs/2410.11494</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2410.11494 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2410.11494 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computation and Language Type: general – SubjectFull: Computer Science - Artificial Intelligence Type: general Titles: – TitleFull: DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Kim, Jinyoung – PersonEntity: Name: NameFull: Ko, Dayoon – PersonEntity: Name: NameFull: Kim, Gunhee IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 10 Type: published Y: 2024 |
| ResultId | 1 |