BERTtoCNN: Similarity-preserving enhanced knowledge distillation for stance detection.
In recent years, text sentiment analysis has attracted wide attention, and promoted the rise and development of stance detection research. The purpose of stance detection is to determine the author's stance (favor or against) towards a specific target or proposition in the text. Pre-trained lan...
Enregistré dans:
Auteurs principaux: | Yang Li, Yuqing Sun, Nana Zhu |
---|---|
Format: | article |
Langue: | EN |
Publié: |
Public Library of Science (PLoS)
2021
|
Sujets: | |
Accès en ligne: | https://doaj.org/article/20905e10c23048df9ce82dda4d80aa51 |
Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
-
Feature fusion-based collaborative learning for knowledge distillation
par: Yiting Li, et autres
Publié: (2021) -
SubStance
Publié: (1971) -
Compressing deep graph convolution network with multi-staged knowledge distillation.
par: Junghun Kim, et autres
Publié: (2021) -
Knowledge Distillation of Grassmann Manifold Network for Remote Sensing Scene Classification
par: Ling Tian, et autres
Publié: (2021) -
A Phenomenology of Social Stances
par: Gian Paolo Terravecchia
Publié: (2016)