Matches in SemOpenAlex for { <https://semopenalex.org/work/W2977607323> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2977607323 abstract "Recurrent Neural Networks (RNNs) have shown promising results in many text generation tasks with their ability in modeling complex data distribution. However, the text generation model in their encoder or decoder RNNs still can not use the context efficiently. In this paper, we propose a novel Attention Recurrent Unit (ARU) to generate short descriptive texts conditioned on database records. Different from conventional approaches Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), ARU allows the context information from the encoder to be aligned first inside the unit, which can improve the ability of content selection and surface realization for the model. And we also design a method called DoubleAtten to enhance the attention distribution when computing the generation probabilities. On the recently released ROTOWIRE dataset, extensive experimental results demonstrate that the ARU and DoubleAtten can efficiently improve the model performance for data-to-text generation task." @default.
- W2977607323 created "2019-10-10" @default.
- W2977607323 creator A5000769066 @default.
- W2977607323 creator A5056706680 @default.
- W2977607323 creator A5076699095 @default.
- W2977607323 creator A5077174181 @default.
- W2977607323 date "2019-07-01" @default.
- W2977607323 modified "2023-09-27" @default.
- W2977607323 title "Data-to-Text Generation with Attention Recurrent Unit" @default.
- W2977607323 cites W1689711448 @default.
- W2977607323 cites W1902237438 @default.
- W2977607323 cites W1985610876 @default.
- W2977607323 cites W2033810442 @default.
- W2977607323 cites W2064675550 @default.
- W2977607323 cites W2116716943 @default.
- W2977607323 cites W2157331557 @default.
- W2977607323 cites W2530887700 @default.
- W2977607323 cites W2550553598 @default.
- W2977607323 cites W2565703912 @default.
- W2977607323 cites W2606974598 @default.
- W2977607323 cites W2739046565 @default.
- W2977607323 cites W2962944953 @default.
- W2977607323 cites W2962955856 @default.
- W2977607323 cites W2962965405 @default.
- W2977607323 cites W2963091658 @default.
- W2977607323 cites W2963290255 @default.
- W2977607323 cites W2963599677 @default.
- W2977607323 cites W2963912046 @default.
- W2977607323 cites W2964165364 @default.
- W2977607323 cites W2964213788 @default.
- W2977607323 cites W2964298349 @default.
- W2977607323 cites W4254816979 @default.
- W2977607323 doi "https://doi.org/10.1109/ijcnn.2019.8852343" @default.
- W2977607323 hasPublicationYear "2019" @default.
- W2977607323 type Work @default.
- W2977607323 sameAs 2977607323 @default.
- W2977607323 citedByCount "4" @default.
- W2977607323 countsByYear W29776073232020 @default.
- W2977607323 countsByYear W29776073232021 @default.
- W2977607323 countsByYear W29776073232022 @default.
- W2977607323 crossrefType "proceedings-article" @default.
- W2977607323 hasAuthorship W2977607323A5000769066 @default.
- W2977607323 hasAuthorship W2977607323A5056706680 @default.
- W2977607323 hasAuthorship W2977607323A5076699095 @default.
- W2977607323 hasAuthorship W2977607323A5077174181 @default.
- W2977607323 hasConcept C122637931 @default.
- W2977607323 hasConcept C145420912 @default.
- W2977607323 hasConcept C154945302 @default.
- W2977607323 hasConcept C15744967 @default.
- W2977607323 hasConcept C204321447 @default.
- W2977607323 hasConcept C41008148 @default.
- W2977607323 hasConceptScore W2977607323C122637931 @default.
- W2977607323 hasConceptScore W2977607323C145420912 @default.
- W2977607323 hasConceptScore W2977607323C154945302 @default.
- W2977607323 hasConceptScore W2977607323C15744967 @default.
- W2977607323 hasConceptScore W2977607323C204321447 @default.
- W2977607323 hasConceptScore W2977607323C41008148 @default.
- W2977607323 hasLocation W29776073231 @default.
- W2977607323 hasOpenAccess W2977607323 @default.
- W2977607323 hasPrimaryLocation W29776073231 @default.
- W2977607323 hasRelatedWork W1552159754 @default.
- W2977607323 hasRelatedWork W2131420137 @default.
- W2977607323 hasRelatedWork W2148757832 @default.
- W2977607323 hasRelatedWork W2151447942 @default.
- W2977607323 hasRelatedWork W2293457016 @default.
- W2977607323 hasRelatedWork W2368651715 @default.
- W2977607323 hasRelatedWork W2611614995 @default.
- W2977607323 hasRelatedWork W2789919619 @default.
- W2977607323 hasRelatedWork W3107474891 @default.
- W2977607323 hasRelatedWork W3169305685 @default.
- W2977607323 isParatext "false" @default.
- W2977607323 isRetracted "false" @default.
- W2977607323 magId "2977607323" @default.
- W2977607323 workType "article" @default.