Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037463749> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3037463749 endingPage "13844" @default.
- W3037463749 startingPage "13843" @default.
- W3037463749 abstract "Multiple-Choice Question Answering (MCQA) is the most challenging area of Machine Reading Comprehension (MRC) and Question Answering (QA), since it not only requires natural language understanding, but also problem-solving techniques. We propose a novel method, Wrong Answer Ensemble (WAE), which can be applied to various MCQA tasks easily. To improve performance of MCQA tasks, humans intuitively exclude unlikely options to solve the MCQA problem. Mimicking this strategy, we train our model with the wrong answer loss and correct answer loss to generalize the features of our model, and exclude likely but wrong options. An experiment on a dialogue-based examination dataset shows the effectiveness of our approach. Our method improves the results on a fine-tuned transformer by 2.7%." @default.
- W3037463749 created "2020-07-02" @default.
- W3037463749 creator A5065856469 @default.
- W3037463749 creator A5082312761 @default.
- W3037463749 date "2020-04-03" @default.
- W3037463749 modified "2023-09-26" @default.
- W3037463749 title "Learning to Classify the Wrong Answers for Multiple Choice Question Answering (Student Abstract)" @default.
- W3037463749 doi "https://doi.org/10.1609/aaai.v34i10.7194" @default.
- W3037463749 hasPublicationYear "2020" @default.
- W3037463749 type Work @default.
- W3037463749 sameAs 3037463749 @default.
- W3037463749 citedByCount "8" @default.
- W3037463749 countsByYear W30374637492020 @default.
- W3037463749 countsByYear W30374637492021 @default.
- W3037463749 countsByYear W30374637492022 @default.
- W3037463749 crossrefType "journal-article" @default.
- W3037463749 hasAuthorship W3037463749A5065856469 @default.
- W3037463749 hasAuthorship W3037463749A5082312761 @default.
- W3037463749 hasBestOaLocation W30374637491 @default.
- W3037463749 hasConcept C119857082 @default.
- W3037463749 hasConcept C121332964 @default.
- W3037463749 hasConcept C138885662 @default.
- W3037463749 hasConcept C154945302 @default.
- W3037463749 hasConcept C165801399 @default.
- W3037463749 hasConcept C176730311 @default.
- W3037463749 hasConcept C199360897 @default.
- W3037463749 hasConcept C204321447 @default.
- W3037463749 hasConcept C2778780117 @default.
- W3037463749 hasConcept C2988416141 @default.
- W3037463749 hasConcept C3019144022 @default.
- W3037463749 hasConcept C41008148 @default.
- W3037463749 hasConcept C41895202 @default.
- W3037463749 hasConcept C44291984 @default.
- W3037463749 hasConcept C511192102 @default.
- W3037463749 hasConcept C554936623 @default.
- W3037463749 hasConcept C62520636 @default.
- W3037463749 hasConcept C66322947 @default.
- W3037463749 hasConceptScore W3037463749C119857082 @default.
- W3037463749 hasConceptScore W3037463749C121332964 @default.
- W3037463749 hasConceptScore W3037463749C138885662 @default.
- W3037463749 hasConceptScore W3037463749C154945302 @default.
- W3037463749 hasConceptScore W3037463749C165801399 @default.
- W3037463749 hasConceptScore W3037463749C176730311 @default.
- W3037463749 hasConceptScore W3037463749C199360897 @default.
- W3037463749 hasConceptScore W3037463749C204321447 @default.
- W3037463749 hasConceptScore W3037463749C2778780117 @default.
- W3037463749 hasConceptScore W3037463749C2988416141 @default.
- W3037463749 hasConceptScore W3037463749C3019144022 @default.
- W3037463749 hasConceptScore W3037463749C41008148 @default.
- W3037463749 hasConceptScore W3037463749C41895202 @default.
- W3037463749 hasConceptScore W3037463749C44291984 @default.
- W3037463749 hasConceptScore W3037463749C511192102 @default.
- W3037463749 hasConceptScore W3037463749C554936623 @default.
- W3037463749 hasConceptScore W3037463749C62520636 @default.
- W3037463749 hasConceptScore W3037463749C66322947 @default.
- W3037463749 hasIssue "10" @default.
- W3037463749 hasLocation W30374637491 @default.
- W3037463749 hasOpenAccess W3037463749 @default.
- W3037463749 hasPrimaryLocation W30374637491 @default.
- W3037463749 hasRelatedWork W2034513866 @default.
- W3037463749 hasRelatedWork W2897789462 @default.
- W3037463749 hasRelatedWork W3000271051 @default.
- W3037463749 hasRelatedWork W3016178088 @default.
- W3037463749 hasRelatedWork W3032797759 @default.
- W3037463749 hasRelatedWork W3037463749 @default.
- W3037463749 hasRelatedWork W3078268584 @default.
- W3037463749 hasRelatedWork W346324049 @default.
- W3037463749 hasRelatedWork W4225147723 @default.
- W3037463749 hasRelatedWork W4288365681 @default.
- W3037463749 hasVolume "34" @default.
- W3037463749 isParatext "false" @default.
- W3037463749 isRetracted "false" @default.
- W3037463749 magId "3037463749" @default.
- W3037463749 workType "article" @default.