Matches in SemOpenAlex for { <https://semopenalex.org/work/W2974149596> ?p ?o ?g. }
- W2974149596 abstract "Given the recent progress in language modeling using Transformer-based neural models and an active interest in generating stylized text, we present an approach to leverage the generalization capabilities of a language model to rewrite an input text in a target author's style. Our proposed approach adapts a pre-trained language model to generate author-stylized text by fine-tuning on the author-specific corpus using a denoising autoencoder (DAE) loss in a cascaded encoder-decoder framework. Optimizing over DAE loss allows our model to learn the nuances of an author's style without relying on parallel data, which has been a severe limitation of the previous related works in this space. To evaluate the efficacy of our approach, we propose a linguistically-motivated framework to quantify stylistic alignment of the generated text to the target author at lexical, syntactic and surface levels. The evaluation framework is both interpretable as it leads to several insights about the model, and self-contained as it does not rely on external classifiers, e.g. sentiment or formality classifiers. Qualitative and quantitative assessment indicates that the proposed approach rewrites the input text with better alignment to the target style while preserving the original content better than state-of-the-art baselines." @default.
- W2974149596 created "2019-09-26" @default.
- W2974149596 creator A5016194897 @default.
- W2974149596 creator A5059650977 @default.
- W2974149596 creator A5073786634 @default.
- W2974149596 creator A5073911898 @default.
- W2974149596 creator A5087775309 @default.
- W2974149596 date "2019-09-22" @default.
- W2974149596 modified "2023-09-27" @default.
- W2974149596 title "Adapting Language Models for Non-Parallel Author-Stylized Rewriting" @default.
- W2974149596 cites W1879024793 @default.
- W2974149596 cites W189559790 @default.
- W2974149596 cites W1939882552 @default.
- W2974149596 cites W2022204871 @default.
- W2974149596 cites W2084807254 @default.
- W2974149596 cites W2101105183 @default.
- W2974149596 cites W2116899917 @default.
- W2974149596 cites W2131526828 @default.
- W2974149596 cites W2133365465 @default.
- W2974149596 cites W2133564696 @default.
- W2974149596 cites W2146888100 @default.
- W2974149596 cites W2152917816 @default.
- W2974149596 cites W2154652894 @default.
- W2974149596 cites W2462831000 @default.
- W2974149596 cites W2735574368 @default.
- W2974149596 cites W2897827272 @default.
- W2974149596 cites W2898799786 @default.
- W2974149596 cites W2914120296 @default.
- W2974149596 cites W2927085091 @default.
- W2974149596 cites W2949696181 @default.
- W2974149596 cites W2952468927 @default.
- W2974149596 cites W2952566153 @default.
- W2974149596 cites W2962753250 @default.
- W2974149596 cites W2962784628 @default.
- W2974149596 cites W2963026768 @default.
- W2974149596 cites W2963062932 @default.
- W2974149596 cites W2963241138 @default.
- W2974149596 cites W2963341956 @default.
- W2974149596 cites W2963366196 @default.
- W2974149596 cites W2963403868 @default.
- W2974149596 cites W2963631950 @default.
- W2974149596 cites W2963667126 @default.
- W2974149596 cites W2964008635 @default.
- W2974149596 cites W2964121744 @default.
- W2974149596 cites W2964222296 @default.
- W2974149596 cites W2964321064 @default.
- W2974149596 cites W2964331441 @default.
- W2974149596 cites W2973330127 @default.
- W2974149596 cites W2080675590 @default.
- W2974149596 hasPublicationYear "2019" @default.
- W2974149596 type Work @default.
- W2974149596 sameAs 2974149596 @default.
- W2974149596 citedByCount "2" @default.
- W2974149596 countsByYear W29741495962020 @default.
- W2974149596 crossrefType "posted-content" @default.
- W2974149596 hasAuthorship W2974149596A5016194897 @default.
- W2974149596 hasAuthorship W2974149596A5059650977 @default.
- W2974149596 hasAuthorship W2974149596A5073786634 @default.
- W2974149596 hasAuthorship W2974149596A5073911898 @default.
- W2974149596 hasAuthorship W2974149596A5087775309 @default.
- W2974149596 hasConcept C101738243 @default.
- W2974149596 hasConcept C108583219 @default.
- W2974149596 hasConcept C111919701 @default.
- W2974149596 hasConcept C118505674 @default.
- W2974149596 hasConcept C121332964 @default.
- W2974149596 hasConcept C134306372 @default.
- W2974149596 hasConcept C137293760 @default.
- W2974149596 hasConcept C138885662 @default.
- W2974149596 hasConcept C139719470 @default.
- W2974149596 hasConcept C153083717 @default.
- W2974149596 hasConcept C154690210 @default.
- W2974149596 hasConcept C154945302 @default.
- W2974149596 hasConcept C162324750 @default.
- W2974149596 hasConcept C165801399 @default.
- W2974149596 hasConcept C177148314 @default.
- W2974149596 hasConcept C199360897 @default.
- W2974149596 hasConcept C204321447 @default.
- W2974149596 hasConcept C2777159308 @default.
- W2974149596 hasConcept C33923547 @default.
- W2974149596 hasConcept C38935604 @default.
- W2974149596 hasConcept C41008148 @default.
- W2974149596 hasConcept C41895202 @default.
- W2974149596 hasConcept C62520636 @default.
- W2974149596 hasConcept C66322947 @default.
- W2974149596 hasConceptScore W2974149596C101738243 @default.
- W2974149596 hasConceptScore W2974149596C108583219 @default.
- W2974149596 hasConceptScore W2974149596C111919701 @default.
- W2974149596 hasConceptScore W2974149596C118505674 @default.
- W2974149596 hasConceptScore W2974149596C121332964 @default.
- W2974149596 hasConceptScore W2974149596C134306372 @default.
- W2974149596 hasConceptScore W2974149596C137293760 @default.
- W2974149596 hasConceptScore W2974149596C138885662 @default.
- W2974149596 hasConceptScore W2974149596C139719470 @default.
- W2974149596 hasConceptScore W2974149596C153083717 @default.
- W2974149596 hasConceptScore W2974149596C154690210 @default.
- W2974149596 hasConceptScore W2974149596C154945302 @default.
- W2974149596 hasConceptScore W2974149596C162324750 @default.
- W2974149596 hasConceptScore W2974149596C165801399 @default.
- W2974149596 hasConceptScore W2974149596C177148314 @default.
- W2974149596 hasConceptScore W2974149596C199360897 @default.