Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034827881> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3034827881 abstract "Due to the improvement of Language Modeling, the emerging NLP assistant tools aiming for text generation greatly reduce the human workload on writing documents. However, the generation of legal text faces greater challenges than ordinary texts because of its high requirement for keeping logic reasonable, which can not be guaranteed by Language Modeling right now. To generate reasonable legal documents, we propose a novel method CoLMQA, which (1) combines Language Modeling and Question Answering, (2) generates text with slots by Language Modeling, and (3) fills the slots by our proposed Question Answering method named Transformer-based Key-Value Memory Networks. In CoLMQA, the slots represent the text part that needs to be highly constrained by logic, such as the name of the law and the number of the law article. And the Question Answering fills the slots in context with the help of Legal Knowledge Base to keep logic reasonable. The experiment verifies the quality of legal documents generated by CoLMQA, surpassing the documents generated by pure Language Modeling." @default.
- W3034827881 created "2020-06-19" @default.
- W3034827881 creator A5015585843 @default.
- W3034827881 creator A5016038454 @default.
- W3034827881 creator A5039717115 @default.
- W3034827881 creator A5047199971 @default.
- W3034827881 creator A5049905128 @default.
- W3034827881 creator A5059364615 @default.
- W3034827881 creator A5068672896 @default.
- W3034827881 date "2020-07-01" @default.
- W3034827881 modified "2023-10-18" @default.
- W3034827881 title "Generating Reasonable Legal Text through the Combination of Language Modeling and Question Answering" @default.
- W3034827881 cites W2020073413 @default.
- W3034827881 cites W2064675550 @default.
- W3034827881 cites W2252136820 @default.
- W3034827881 cites W2945259830 @default.
- W3034827881 cites W2945844671 @default.
- W3034827881 cites W2951008357 @default.
- W3034827881 cites W2951048068 @default.
- W3034827881 cites W2962940365 @default.
- W3034827881 cites W2963341956 @default.
- W3034827881 cites W2963403868 @default.
- W3034827881 cites W2963448850 @default.
- W3034827881 cites W2963475460 @default.
- W3034827881 cites W2964059756 @default.
- W3034827881 cites W2970609357 @default.
- W3034827881 cites W2995346997 @default.
- W3034827881 cites W2998557616 @default.
- W3034827881 doi "https://doi.org/10.24963/ijcai.2020/510" @default.
- W3034827881 hasPublicationYear "2020" @default.
- W3034827881 type Work @default.
- W3034827881 sameAs 3034827881 @default.
- W3034827881 citedByCount "5" @default.
- W3034827881 countsByYear W30348278812021 @default.
- W3034827881 countsByYear W30348278812022 @default.
- W3034827881 crossrefType "proceedings-article" @default.
- W3034827881 hasAuthorship W3034827881A5015585843 @default.
- W3034827881 hasAuthorship W3034827881A5016038454 @default.
- W3034827881 hasAuthorship W3034827881A5039717115 @default.
- W3034827881 hasAuthorship W3034827881A5047199971 @default.
- W3034827881 hasAuthorship W3034827881A5049905128 @default.
- W3034827881 hasAuthorship W3034827881A5059364615 @default.
- W3034827881 hasAuthorship W3034827881A5068672896 @default.
- W3034827881 hasBestOaLocation W30348278811 @default.
- W3034827881 hasConcept C119599485 @default.
- W3034827881 hasConcept C127413603 @default.
- W3034827881 hasConcept C137293760 @default.
- W3034827881 hasConcept C151730666 @default.
- W3034827881 hasConcept C154945302 @default.
- W3034827881 hasConcept C165801399 @default.
- W3034827881 hasConcept C204321447 @default.
- W3034827881 hasConcept C26517878 @default.
- W3034827881 hasConcept C2779343474 @default.
- W3034827881 hasConcept C38652104 @default.
- W3034827881 hasConcept C41008148 @default.
- W3034827881 hasConcept C44291984 @default.
- W3034827881 hasConcept C66322947 @default.
- W3034827881 hasConcept C86803240 @default.
- W3034827881 hasConceptScore W3034827881C119599485 @default.
- W3034827881 hasConceptScore W3034827881C127413603 @default.
- W3034827881 hasConceptScore W3034827881C137293760 @default.
- W3034827881 hasConceptScore W3034827881C151730666 @default.
- W3034827881 hasConceptScore W3034827881C154945302 @default.
- W3034827881 hasConceptScore W3034827881C165801399 @default.
- W3034827881 hasConceptScore W3034827881C204321447 @default.
- W3034827881 hasConceptScore W3034827881C26517878 @default.
- W3034827881 hasConceptScore W3034827881C2779343474 @default.
- W3034827881 hasConceptScore W3034827881C38652104 @default.
- W3034827881 hasConceptScore W3034827881C41008148 @default.
- W3034827881 hasConceptScore W3034827881C44291984 @default.
- W3034827881 hasConceptScore W3034827881C66322947 @default.
- W3034827881 hasConceptScore W3034827881C86803240 @default.
- W3034827881 hasLocation W30348278811 @default.
- W3034827881 hasOpenAccess W3034827881 @default.
- W3034827881 hasPrimaryLocation W30348278811 @default.
- W3034827881 hasRelatedWork W2936497627 @default.
- W3034827881 hasRelatedWork W2964413124 @default.
- W3034827881 hasRelatedWork W3013624417 @default.
- W3034827881 hasRelatedWork W3049463507 @default.
- W3034827881 hasRelatedWork W3098382480 @default.
- W3034827881 hasRelatedWork W3204607391 @default.
- W3034827881 hasRelatedWork W4287598411 @default.
- W3034827881 hasRelatedWork W4287826556 @default.
- W3034827881 hasRelatedWork W4288365749 @default.
- W3034827881 hasRelatedWork W4381058564 @default.
- W3034827881 isParatext "false" @default.
- W3034827881 isRetracted "false" @default.
- W3034827881 magId "3034827881" @default.
- W3034827881 workType "article" @default.