Cargando…
Multiturn dialogue generation by modeling sentence-level and discourse-level contexts
Currently, multiturn dialogue models generate human-like responses based on pretrained language models given a dialogue history. However, most existing models simply concatenate dialogue histories, which makes it difficult to maintain a high degree of consistency throughout the generated text. We sp...
Autores principales: | Yang, Yang, Cao, Juan, Wen, Yujun, Zhang, Pengzhou |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9701771/ https://www.ncbi.nlm.nih.gov/pubmed/36437277 http://dx.doi.org/10.1038/s41598-022-24787-1 |
Ejemplares similares
-
Functional and anatomical correlates of word-, sentence-, and discourse-level integration in sign language
por: Inubushi, Tomoo, et al.
Publicado: (2013) -
Table to text generation with accurate content copying
por: Yang, Yang, et al.
Publicado: (2021) -
The Contribution of Word-, Sentence-, and Discourse-Level Abilities on Writing Performance: A 3-Year Longitudinal Study
por: Carvalhais, Lénia, et al.
Publicado: (2021) -
Multiturn Measurements at the CERN SPS
por: Klem, J T, et al.
Publicado: (2000) -
Elaboration over a Discourse Facilitates Retrieval in Sentence Processing
por: Troyer, Melissa, et al.
Publicado: (2016)