Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism
Neural auto-regressive sequence-to-sequence models have been dominant in text generation tasks, especially the question generation task. However, neural generation models suffer from the global and local semantic semantic drift problems. Hence, we propose the hierarchical encoding–decoding mechanism...
Guardado en:
Autores principales: | Tianbo Ji, Chenyang Lyu, Zhichao Cao, Peng Cheng |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/9ea3193bfe014b1ba4773bde0b5c6f0d |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Gauge-dependent topology in non-reciprocal hopping systems with pseudo-Hermitian symmetry
por: Xintong Zhang, et al.
Publicado: (2021) -
Antiferromagnetic spatial photonic Ising machine through optoelectronic correlation computing
por: Junyi Huang, et al.
Publicado: (2021) -
Cryptography in Hierarchical Coded Caching: System Model and Cost Analysis
por: Behrouz Zolfaghari, et al.
Publicado: (2021) -
A Manifold Learning Perspective on Representation Learning: Learning Decoder and Representations without an Encoder
por: Viktoria Schuster, et al.
Publicado: (2021) -
Spin-orbit torque switching of chiral magnetization across a synthetic antiferromagnet
por: Kang Wang, et al.
Publicado: (2021)