Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216576322> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W3216576322 endingPage "93" @default.
- W3216576322 startingPage "93" @default.
- W3216576322 abstract "Question generation is a conditioned language generation task that consists in generating a context-aware question given a context and the targeted answer. Train language modelling with a mere likelihood maximization has been widely used while suffering from exposure bias and the discordance between the training and the test metrics. In the way of addressing this issue, The presented work portrays a fully Transformer-based reinforcement learning generator-evaluation architecture for neural question generation. To edge the flexibility of the generation, a semantic-based reward score was externally infused during the training to drive the training of the language model. The global architecture is laid out in a generator-evaluator fashion optimized directly to n-gram and semantic-based metrics. Evaluation metrics for language modelling only based on n-gram overlapping do not consider semantic relations between reference and candidate sequences. To improve the evaluation step, a two-fold evaluation was carried out. On the one side, an n-gram overlapping evaluation using the BLEU score. On the other side, a semantic-based assessment using BERTScore and NUBIA. The results were corroborated by a binary human evaluation of the semantic relatedness of the generated question and the ground truth. The results obtained showed that use a semantic-based REINFORCE algorithm for the question generation syntactically reshapes the generated questions while preserving their underlying semantic meaning. Many downstream applications can be drawn from a successful question generation including the enlargement of question answering datasets, the improvement of conversational systems, the enhancement of autonomous educational assessment systems, and so forth." @default.
- W3216576322 created "2021-12-06" @default.
- W3216576322 creator A5021058044 @default.
- W3216576322 date "2021-01-01" @default.
- W3216576322 modified "2023-09-25" @default.
- W3216576322 title "Semantic-Based Self-Critical Training for Question Generation" @default.
- W3216576322 doi "https://doi.org/10.11648/j.ajist.20210504.12" @default.
- W3216576322 hasPublicationYear "2021" @default.
- W3216576322 type Work @default.
- W3216576322 sameAs 3216576322 @default.
- W3216576322 citedByCount "0" @default.
- W3216576322 crossrefType "journal-article" @default.
- W3216576322 hasAuthorship W3216576322A5021058044 @default.
- W3216576322 hasBestOaLocation W32165763221 @default.
- W3216576322 hasConcept C119857082 @default.
- W3216576322 hasConcept C121332964 @default.
- W3216576322 hasConcept C137293760 @default.
- W3216576322 hasConcept C154945302 @default.
- W3216576322 hasConcept C165801399 @default.
- W3216576322 hasConcept C204321447 @default.
- W3216576322 hasConcept C41008148 @default.
- W3216576322 hasConcept C62520636 @default.
- W3216576322 hasConcept C66322947 @default.
- W3216576322 hasConceptScore W3216576322C119857082 @default.
- W3216576322 hasConceptScore W3216576322C121332964 @default.
- W3216576322 hasConceptScore W3216576322C137293760 @default.
- W3216576322 hasConceptScore W3216576322C154945302 @default.
- W3216576322 hasConceptScore W3216576322C165801399 @default.
- W3216576322 hasConceptScore W3216576322C204321447 @default.
- W3216576322 hasConceptScore W3216576322C41008148 @default.
- W3216576322 hasConceptScore W3216576322C62520636 @default.
- W3216576322 hasConceptScore W3216576322C66322947 @default.
- W3216576322 hasIssue "4" @default.
- W3216576322 hasLocation W32165763221 @default.
- W3216576322 hasOpenAccess W3216576322 @default.
- W3216576322 hasPrimaryLocation W32165763221 @default.
- W3216576322 hasRelatedWork W1022496157 @default.
- W3216576322 hasRelatedWork W1503858070 @default.
- W3216576322 hasRelatedWork W1571404427 @default.
- W3216576322 hasRelatedWork W1602608327 @default.
- W3216576322 hasRelatedWork W1846229318 @default.
- W3216576322 hasRelatedWork W2078014983 @default.
- W3216576322 hasRelatedWork W2755192592 @default.
- W3216576322 hasRelatedWork W2983766097 @default.
- W3216576322 hasRelatedWork W3107474891 @default.
- W3216576322 hasRelatedWork W2613333037 @default.
- W3216576322 hasVolume "5" @default.
- W3216576322 isParatext "false" @default.
- W3216576322 isRetracted "false" @default.
- W3216576322 magId "3216576322" @default.
- W3216576322 workType "article" @default.