ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation
Plug-and-play language models (PPLMs) enable topic-conditioned natural language generation by combining large pre-trained generators with attribute models to steer the predicted token distribution towards selected topics. Despite their efficiency, the large amounts of labeled texts required by PPLMs...
Guardado en:
Autores principales: | Ginevra Carbone, Gabriele Sarti |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Accademia University Press
2020
|
Materias: | |
Acceso en línea: | https://doaj.org/article/b2ee41dfd19944018b6d50a4d4719516 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Introduction to the Special Issue on Natural Language and Learning Machines
por: Dan Roth, et al.
Publicado: (2017) -
Entities as Topic Labels: Combining Entity Linking and Labeled LDA to Improve Topic Interpretability and Evaluability
por: Anne Lauscher, et al.
Publicado: (2016) -
Geometric and Statistical Analysis of Emotions and Topics in Corpora
por: Francesco Tarasconi, et al.
Publicado: (2015) -
Emerging Topics at the Fourth Italian Conference on Computational Linguistics
por: Roberto Basili, et al.
Publicado: (2018) -
Emerging Topics from the Fifth Italian Conference on Computational Linguistics
por: Roberto Basili, et al.
Publicado: (2019)