PU-GEN: Enhancing generative commonsense reasoning for language models with human-centered knowledge
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Seo, Jaehyung | - |
dc.contributor.author | Oh, Dongsuk | - |
dc.contributor.author | Eo, Sugyeong | - |
dc.contributor.author | Park, Chanjun | - |
dc.contributor.author | Yang, Kisu | - |
dc.contributor.author | Moon, Hyeonseok | - |
dc.contributor.author | Park, Kinam | - |
dc.contributor.author | Lim, Heuiseok | - |
dc.date.accessioned | 2022-11-17T10:41:03Z | - |
dc.date.available | 2022-11-17T10:41:03Z | - |
dc.date.created | 2022-11-17 | - |
dc.date.issued | 2022-11-28 | - |
dc.identifier.issn | 0950-7051 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/145629 | - |
dc.description.abstract | Generative commonsense reasoning refers to the ability of a language model to generate a sentence with a given concept-set based on compositional generalization and commonsense reasoning. In the CommonGen challenge, which evaluates the capability of generative commonsense reasoning, language models continue to exhibit low performances and struggle to leverage knowledge representation from humans. Therefore, we propose PU-GEN to leverage human-centered knowledge in language models to enhance compositional generalization and commonsense reasoning considering the human language generation process. To incorporate human-centered knowledge, PU-GEN reinterprets two linguistic philosophies from Wittgenstein: picture theory and use theory. First, we retrieve scene knowledge to reflect picture theory such that a model can describe a general situation as if it were being painted. Second, we extend relational knowledge to consider use theory for understanding various contexts. PU-GEN demonstrates superior performance in qualitative and quantitative evaluations over baseline models in CommonGen and generates convincing evidence for CommonsenseQA. Moreover, it outperforms the state-of-the-art model used in the previous CommonGen challenge.(c) 2022 Elsevier B.V. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER | - |
dc.title | PU-GEN: Enhancing generative commonsense reasoning for language models with human-centered knowledge | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lim, Heuiseok | - |
dc.identifier.doi | 10.1016/j.knosys.2022.109861 | - |
dc.identifier.scopusid | 2-s2.0-85138031965 | - |
dc.identifier.wosid | 000860566400007 | - |
dc.identifier.bibliographicCitation | KNOWLEDGE-BASED SYSTEMS, v.256 | - |
dc.relation.isPartOf | KNOWLEDGE-BASED SYSTEMS | - |
dc.citation.title | KNOWLEDGE-BASED SYSTEMS | - |
dc.citation.volume | 256 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.subject.keywordAuthor | Text generation | - |
dc.subject.keywordAuthor | Commonsense reasoning | - |
dc.subject.keywordAuthor | Human-centered knowledge | - |
dc.subject.keywordAuthor | Language model | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.