Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890961898> ?p ?o ?g. }
- W2890961898 abstract "Open Domain Question Answering (QA) is evolving from complex pipelined systems to end-to-end deep neural networks. Specialized neural models have been developed for extracting answers from either text alone or Knowledge Bases (KBs) alone. In this paper we look at a more practical setting, namely QA over the combination of a KB and entity-linked text, which is appropriate when an incomplete KB is available with a large text corpus. Building on recent advances in graph representation learning we propose a novel model, GRAFT-Net, for extracting answers from a question-specific subgraph containing text and KB entities and relations. We construct a suite of benchmark tasks for this problem, varying the difficulty of questions, the amount of training data, and KB completeness. We show that GRAFT-Net is competitive with the state-of-the-art when tested using either KBs or text alone, and vastly outperforms existing methods in the combined setting." @default.
- W2890961898 created "2018-09-27" @default.
- W2890961898 creator A5018931712 @default.
- W2890961898 creator A5051350580 @default.
- W2890961898 creator A5051617344 @default.
- W2890961898 creator A5055033421 @default.
- W2890961898 creator A5069067033 @default.
- W2890961898 creator A5071983998 @default.
- W2890961898 date "2018-01-01" @default.
- W2890961898 modified "2023-10-12" @default.
- W2890961898 title "Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text" @default.
- W2890961898 cites W102708294 @default.
- W2890961898 cites W1852412531 @default.
- W2890961898 cites W1950142954 @default.
- W2890961898 cites W2044938180 @default.
- W2890961898 cites W2094728533 @default.
- W2890961898 cites W2116341502 @default.
- W2890961898 cites W2170344111 @default.
- W2890961898 cites W2171278097 @default.
- W2890961898 cites W2250635077 @default.
- W2890961898 cites W2251960799 @default.
- W2890961898 cites W2471900581 @default.
- W2890961898 cites W2511149293 @default.
- W2890961898 cites W2521709538 @default.
- W2890961898 cites W2546950329 @default.
- W2890961898 cites W2551396370 @default.
- W2890961898 cites W2567619939 @default.
- W2890961898 cites W2604314403 @default.
- W2890961898 cites W2604890851 @default.
- W2890961898 cites W2606780347 @default.
- W2890961898 cites W2612228435 @default.
- W2890961898 cites W2613681825 @default.
- W2890961898 cites W2624431344 @default.
- W2890961898 cites W2734823783 @default.
- W2890961898 cites W2753329127 @default.
- W2890961898 cites W2769099080 @default.
- W2890961898 cites W2798150812 @default.
- W2890961898 cites W2798681242 @default.
- W2890961898 cites W2950898568 @default.
- W2890961898 cites W2963175042 @default.
- W2890961898 cites W2963195889 @default.
- W2890961898 cites W2963393262 @default.
- W2890961898 cites W2963448850 @default.
- W2890961898 cites W2963488798 @default.
- W2890961898 cites W2963564796 @default.
- W2890961898 cites W2963655104 @default.
- W2890961898 cites W2963748441 @default.
- W2890961898 cites W2963866616 @default.
- W2890961898 cites W2963961334 @default.
- W2890961898 cites W2964059756 @default.
- W2890961898 cites W2964120615 @default.
- W2890961898 cites W2964152081 @default.
- W2890961898 cites W2964224278 @default.
- W2890961898 cites W4919037 @default.
- W2890961898 cites W580074167 @default.
- W2890961898 cites W2607739056 @default.
- W2890961898 doi "https://doi.org/10.18653/v1/d18-1455" @default.
- W2890961898 hasPublicationYear "2018" @default.
- W2890961898 type Work @default.
- W2890961898 sameAs 2890961898 @default.
- W2890961898 citedByCount "239" @default.
- W2890961898 countsByYear W28909618982018 @default.
- W2890961898 countsByYear W28909618982019 @default.
- W2890961898 countsByYear W28909618982020 @default.
- W2890961898 countsByYear W28909618982021 @default.
- W2890961898 countsByYear W28909618982022 @default.
- W2890961898 countsByYear W28909618982023 @default.
- W2890961898 crossrefType "proceedings-article" @default.
- W2890961898 hasAuthorship W2890961898A5018931712 @default.
- W2890961898 hasAuthorship W2890961898A5051350580 @default.
- W2890961898 hasAuthorship W2890961898A5051617344 @default.
- W2890961898 hasAuthorship W2890961898A5055033421 @default.
- W2890961898 hasAuthorship W2890961898A5069067033 @default.
- W2890961898 hasAuthorship W2890961898A5071983998 @default.
- W2890961898 hasBestOaLocation W28909618981 @default.
- W2890961898 hasConcept C108583219 @default.
- W2890961898 hasConcept C132525143 @default.
- W2890961898 hasConcept C13280743 @default.
- W2890961898 hasConcept C134306372 @default.
- W2890961898 hasConcept C154945302 @default.
- W2890961898 hasConcept C166957645 @default.
- W2890961898 hasConcept C17231256 @default.
- W2890961898 hasConcept C185798385 @default.
- W2890961898 hasConcept C199360897 @default.
- W2890961898 hasConcept C204321447 @default.
- W2890961898 hasConcept C205649164 @default.
- W2890961898 hasConcept C23123220 @default.
- W2890961898 hasConcept C2780801425 @default.
- W2890961898 hasConcept C2987255567 @default.
- W2890961898 hasConcept C2993776861 @default.
- W2890961898 hasConcept C33923547 @default.
- W2890961898 hasConcept C36503486 @default.
- W2890961898 hasConcept C41008148 @default.
- W2890961898 hasConcept C44291984 @default.
- W2890961898 hasConcept C79581498 @default.
- W2890961898 hasConcept C80444323 @default.
- W2890961898 hasConcept C95457728 @default.
- W2890961898 hasConceptScore W2890961898C108583219 @default.
- W2890961898 hasConceptScore W2890961898C132525143 @default.
- W2890961898 hasConceptScore W2890961898C13280743 @default.