Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912481627> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W2912481627 abstract "Natural Language Generation (NLG), as an important part of Natural Language Processing (NLP), has begun to take full advantage of recent advances in language models. Based on recurrent neural networks (RNNs), NLG has made ground breaking improvement and is widely applied in many tasks. RNNs typically learn a joint probability of words, and the additional information is usually fed to RNNs hidden layer using implicit vector representations. Still, there exists some problem unsolved. Standard RNN is not applicable when we need to impose hard constraints on the language generation tasks: for example, standard RNNs cannot guarantee designated word(s) to appear in a target sentence to generate. In this paper, we propose a Backward-or-Forward Generative Adversarial Nets model (BoFGAN) to address this problem. Starting from a particular given word, a generative model at every time step generates a new preceding or subsequent word conditioned on the generated sequence so far until both sides reach an end. To train the generator, we first model it as a stochastic policy using Reinforcement Learning; then we employ a discriminator to evaluate the quality of a complete sequence as the end reward; and lastly, we apply Monte Carlo (MC) search to estimate the long-term return and update the generator via policy gradient. Experimental results demonstrate the effectiveness and rationality of our proposed BoFGAN model." @default.
- W2912481627 created "2019-02-21" @default.
- W2912481627 creator A5057256093 @default.
- W2912481627 creator A5077260423 @default.
- W2912481627 creator A5083963821 @default.
- W2912481627 creator A5085230597 @default.
- W2912481627 date "2019-05-13" @default.
- W2912481627 modified "2023-09-23" @default.
- W2912481627 title "BoFGAN: Towards A New Structure of Backward-or-Forward Generative Adversarial Nets" @default.
- W2912481627 cites W179875071 @default.
- W2912481627 cites W2052893955 @default.
- W2912481627 cites W2054177078 @default.
- W2912481627 cites W2079735306 @default.
- W2912481627 cites W2101105183 @default.
- W2912481627 cites W2106087324 @default.
- W2912481627 cites W2124228738 @default.
- W2912481627 cites W2131774270 @default.
- W2912481627 cites W2757121784 @default.
- W2912481627 cites W2889924956 @default.
- W2912481627 cites W2905279751 @default.
- W2912481627 cites W2964008635 @default.
- W2912481627 cites W2966746916 @default.
- W2912481627 doi "https://doi.org/10.1145/3308558.3313734" @default.
- W2912481627 hasPublicationYear "2019" @default.
- W2912481627 type Work @default.
- W2912481627 sameAs 2912481627 @default.
- W2912481627 citedByCount "0" @default.
- W2912481627 crossrefType "proceedings-article" @default.
- W2912481627 hasAuthorship W2912481627A5057256093 @default.
- W2912481627 hasAuthorship W2912481627A5077260423 @default.
- W2912481627 hasAuthorship W2912481627A5083963821 @default.
- W2912481627 hasAuthorship W2912481627A5085230597 @default.
- W2912481627 hasConcept C154945302 @default.
- W2912481627 hasConcept C37736160 @default.
- W2912481627 hasConcept C39890363 @default.
- W2912481627 hasConcept C41008148 @default.
- W2912481627 hasConcept C80444323 @default.
- W2912481627 hasConceptScore W2912481627C154945302 @default.
- W2912481627 hasConceptScore W2912481627C37736160 @default.
- W2912481627 hasConceptScore W2912481627C39890363 @default.
- W2912481627 hasConceptScore W2912481627C41008148 @default.
- W2912481627 hasConceptScore W2912481627C80444323 @default.
- W2912481627 hasLocation W29124816271 @default.
- W2912481627 hasOpenAccess W2912481627 @default.
- W2912481627 hasPrimaryLocation W29124816271 @default.
- W2912481627 hasRelatedWork W2901368259 @default.
- W2912481627 hasRelatedWork W2998996837 @default.
- W2912481627 hasRelatedWork W3017161950 @default.
- W2912481627 hasRelatedWork W3024390022 @default.
- W2912481627 hasRelatedWork W3156291593 @default.
- W2912481627 hasRelatedWork W3164279787 @default.
- W2912481627 hasRelatedWork W4280544492 @default.
- W2912481627 hasRelatedWork W4311460979 @default.
- W2912481627 hasRelatedWork W4313479464 @default.
- W2912481627 hasRelatedWork W4316035501 @default.
- W2912481627 isParatext "false" @default.
- W2912481627 isRetracted "false" @default.
- W2912481627 magId "2912481627" @default.
- W2912481627 workType "article" @default.