Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972807749> ?p ?o ?g. }
- W2972807749 abstract "In this work, we focus on the task of Automatic Question Generation (AQG) where given a passage and an answer the task is to generate the corresponding question. It is desired that the generated question should be (i) grammatically correct (ii) answerable from the passage and (iii) specific to the given answer. An analysis of existing AQG models shows that they produce questions which do not adhere to one or more of {the above-mentioned qualities}. In particular, the generated questions look like an incomplete draft of the desired question with a clear scope for refinement. {To alleviate this shortcoming}, we propose a method which tries to mimic the human process of generating questions by first creating an initial draft and then refining it. More specifically, we propose Refine Network (RefNet) which contains two decoders. The second decoder uses a dual attention network which pays attention to both (i) the original passage and (ii) the question (initial draft) generated by the first decoder. In effect, it refines the question generated by the first decoder, thereby making it more correct and complete. We evaluate RefNet on three datasets, textit{viz.}, SQuAD, HOTPOT-QA, and DROP, and show that it outperforms existing state-of-the-art methods by 7-16% on all of these datasets. Lastly, we show that we can improve the quality of the second decoder on specific metrics, such as, fluency and answerability by explicitly rewarding revisions that improve on the corresponding metric during training. The code has been made publicly available footnote{this https URL}" @default.
- W2972807749 created "2019-09-19" @default.
- W2972807749 creator A5009374923 @default.
- W2972807749 creator A5050036814 @default.
- W2972807749 creator A5059650977 @default.
- W2972807749 creator A5060553255 @default.
- W2972807749 creator A5072683962 @default.
- W2972807749 date "2019-08-31" @default.
- W2972807749 modified "2023-09-27" @default.
- W2972807749 title "Let's Ask Again: Refine Network for Automatic Question Generation." @default.
- W2972807749 cites W1531374185 @default.
- W2972807749 cites W2064675550 @default.
- W2972807749 cites W2070150502 @default.
- W2972807749 cites W2101105183 @default.
- W2972807749 cites W2154652894 @default.
- W2972807749 cites W2250425483 @default.
- W2972807749 cites W2250539671 @default.
- W2972807749 cites W2551396370 @default.
- W2972807749 cites W2606974598 @default.
- W2972807749 cites W2607059968 @default.
- W2972807749 cites W2610891036 @default.
- W2972807749 cites W2612675303 @default.
- W2972807749 cites W2729046720 @default.
- W2972807749 cites W2741253951 @default.
- W2972807749 cites W2752047430 @default.
- W2972807749 cites W2753613501 @default.
- W2972807749 cites W2757715585 @default.
- W2972807749 cites W2759816466 @default.
- W2972807749 cites W2789204155 @default.
- W2972807749 cites W2807750936 @default.
- W2972807749 cites W2889670144 @default.
- W2972807749 cites W2889787757 @default.
- W2972807749 cites W2890166583 @default.
- W2972807749 cites W2891946694 @default.
- W2972807749 cites W2919420119 @default.
- W2972807749 cites W2950700230 @default.
- W2972807749 cites W2953188497 @default.
- W2972807749 cites W2962717047 @default.
- W2972807749 cites W2963084599 @default.
- W2972807749 cites W2963748441 @default.
- W2972807749 cites W2964236999 @default.
- W2972807749 cites W2964308564 @default.
- W2972807749 cites W2964309167 @default.
- W2972807749 cites W803028973 @default.
- W2972807749 cites W2963768805 @default.
- W2972807749 hasPublicationYear "2019" @default.
- W2972807749 type Work @default.
- W2972807749 sameAs 2972807749 @default.
- W2972807749 citedByCount "2" @default.
- W2972807749 countsByYear W29728077492020 @default.
- W2972807749 crossrefType "posted-content" @default.
- W2972807749 hasAuthorship W2972807749A5009374923 @default.
- W2972807749 hasAuthorship W2972807749A5050036814 @default.
- W2972807749 hasAuthorship W2972807749A5059650977 @default.
- W2972807749 hasAuthorship W2972807749A5060553255 @default.
- W2972807749 hasAuthorship W2972807749A5072683962 @default.
- W2972807749 hasConcept C111472728 @default.
- W2972807749 hasConcept C11413529 @default.
- W2972807749 hasConcept C120665830 @default.
- W2972807749 hasConcept C121332964 @default.
- W2972807749 hasConcept C136264566 @default.
- W2972807749 hasConcept C138885662 @default.
- W2972807749 hasConcept C145420912 @default.
- W2972807749 hasConcept C154945302 @default.
- W2972807749 hasConcept C162324750 @default.
- W2972807749 hasConcept C177264268 @default.
- W2972807749 hasConcept C187736073 @default.
- W2972807749 hasConcept C192209626 @default.
- W2972807749 hasConcept C199360897 @default.
- W2972807749 hasConcept C23123220 @default.
- W2972807749 hasConcept C2776760102 @default.
- W2972807749 hasConcept C2777413886 @default.
- W2972807749 hasConcept C2778012447 @default.
- W2972807749 hasConcept C2779530757 @default.
- W2972807749 hasConcept C2780451532 @default.
- W2972807749 hasConcept C33923547 @default.
- W2972807749 hasConcept C41008148 @default.
- W2972807749 hasConcept C80444323 @default.
- W2972807749 hasConcept C90329073 @default.
- W2972807749 hasConceptScore W2972807749C111472728 @default.
- W2972807749 hasConceptScore W2972807749C11413529 @default.
- W2972807749 hasConceptScore W2972807749C120665830 @default.
- W2972807749 hasConceptScore W2972807749C121332964 @default.
- W2972807749 hasConceptScore W2972807749C136264566 @default.
- W2972807749 hasConceptScore W2972807749C138885662 @default.
- W2972807749 hasConceptScore W2972807749C145420912 @default.
- W2972807749 hasConceptScore W2972807749C154945302 @default.
- W2972807749 hasConceptScore W2972807749C162324750 @default.
- W2972807749 hasConceptScore W2972807749C177264268 @default.
- W2972807749 hasConceptScore W2972807749C187736073 @default.
- W2972807749 hasConceptScore W2972807749C192209626 @default.
- W2972807749 hasConceptScore W2972807749C199360897 @default.
- W2972807749 hasConceptScore W2972807749C23123220 @default.
- W2972807749 hasConceptScore W2972807749C2776760102 @default.
- W2972807749 hasConceptScore W2972807749C2777413886 @default.
- W2972807749 hasConceptScore W2972807749C2778012447 @default.
- W2972807749 hasConceptScore W2972807749C2779530757 @default.
- W2972807749 hasConceptScore W2972807749C2780451532 @default.
- W2972807749 hasConceptScore W2972807749C33923547 @default.
- W2972807749 hasConceptScore W2972807749C41008148 @default.