Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090398892> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W3090398892 abstract "Automatic question generation (QG) has found applications in the education sector and to enhance human-machine interactions in chatbots. Existing neural QG models can be categorized into answer-unaware and answer-aware models. One of the main challenges faced by existing neural QG models is the degradation in performance due to the issue of one-to-many mapping, where, given a passage, both answer (query interest/question intent) and auxiliary information (context information present in the question) can result in different questions being generated. We propose a controllable question generation model (CQG) that employs an attentive sequence-to-sequence (seq2seq) based generative model with copying mechanism. The proposed CQG also incorporates query interest and auxiliary information as controllers to address the one-to-many mapping problem in QG. Two variants of embedding strategies are designed for CQG to achieve good performance. To verify its performance, an automatic labeling scheme for harvesting auxiliary information is first developed. A QG dataset is also annotated with auxiliary information from a reading comprehension dataset. Performance evaluation shows that the proposed model not only outperforms existing QG models, it also has the potential to generate multiple questions that are relevant given a single passage." @default.
- W3090398892 created "2020-10-08" @default.
- W3090398892 creator A5010202250 @default.
- W3090398892 creator A5019945476 @default.
- W3090398892 creator A5058967851 @default.
- W3090398892 date "2020-07-01" @default.
- W3090398892 modified "2023-09-27" @default.
- W3090398892 title "Controllable Question Generation via Sequence-to-Sequence Neural Model with Auxiliary Information" @default.
- W3090398892 cites W1606489891 @default.
- W3090398892 cites W1902237438 @default.
- W3090398892 cites W2133459682 @default.
- W3090398892 cites W2250539671 @default.
- W3090398892 cites W2797291779 @default.
- W3090398892 cites W2804292122 @default.
- W3090398892 cites W2889670144 @default.
- W3090398892 cites W2890166583 @default.
- W3090398892 cites W2891946694 @default.
- W3090398892 cites W2911857455 @default.
- W3090398892 cites W2962717047 @default.
- W3090398892 cites W2962944953 @default.
- W3090398892 cites W2962977247 @default.
- W3090398892 cites W2963351776 @default.
- W3090398892 cites W2963748441 @default.
- W3090398892 cites W2964236999 @default.
- W3090398892 cites W2964912036 @default.
- W3090398892 doi "https://doi.org/10.1109/ijcnn48605.2020.9207643" @default.
- W3090398892 hasPublicationYear "2020" @default.
- W3090398892 type Work @default.
- W3090398892 sameAs 3090398892 @default.
- W3090398892 citedByCount "1" @default.
- W3090398892 countsByYear W30903988922022 @default.
- W3090398892 crossrefType "proceedings-article" @default.
- W3090398892 hasAuthorship W3090398892A5010202250 @default.
- W3090398892 hasAuthorship W3090398892A5019945476 @default.
- W3090398892 hasAuthorship W3090398892A5058967851 @default.
- W3090398892 hasConcept C154945302 @default.
- W3090398892 hasConcept C204321447 @default.
- W3090398892 hasConcept C2778112365 @default.
- W3090398892 hasConcept C41008148 @default.
- W3090398892 hasConcept C54355233 @default.
- W3090398892 hasConcept C86803240 @default.
- W3090398892 hasConceptScore W3090398892C154945302 @default.
- W3090398892 hasConceptScore W3090398892C204321447 @default.
- W3090398892 hasConceptScore W3090398892C2778112365 @default.
- W3090398892 hasConceptScore W3090398892C41008148 @default.
- W3090398892 hasConceptScore W3090398892C54355233 @default.
- W3090398892 hasConceptScore W3090398892C86803240 @default.
- W3090398892 hasLocation W30903988921 @default.
- W3090398892 hasOpenAccess W3090398892 @default.
- W3090398892 hasPrimaryLocation W30903988921 @default.
- W3090398892 hasRelatedWork W1552159754 @default.
- W3090398892 hasRelatedWork W2131420137 @default.
- W3090398892 hasRelatedWork W2148757832 @default.
- W3090398892 hasRelatedWork W2151447942 @default.
- W3090398892 hasRelatedWork W2293457016 @default.
- W3090398892 hasRelatedWork W2368651715 @default.
- W3090398892 hasRelatedWork W2611614995 @default.
- W3090398892 hasRelatedWork W2789919619 @default.
- W3090398892 hasRelatedWork W3107474891 @default.
- W3090398892 hasRelatedWork W3169305685 @default.
- W3090398892 isParatext "false" @default.
- W3090398892 isRetracted "false" @default.
- W3090398892 magId "3090398892" @default.
- W3090398892 workType "article" @default.