Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing 2021
DOI: 10.18653/v1/2021.emnlp-main.770
|View full text |Cite
|
Sign up to set email alerts
|

Wasserstein Selective Transfer Learning for Cross-domain Text Mining

Abstract: Transfer learning (TL) seeks to improve the learning of a data-scarce target domain by using information from source domains. However, the source and target domains usually have different data distributions, which may lead to negative transfer. To alleviate this issue, we propose a Wasserstein Selective Transfer Learning (WSTL) method. Specifically, the proposed method considers a reinforced selector to select helpful data for transfer learning. We further use a Wasserstein-based discriminator to maximize the … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(1 citation statement)
references
References 34 publications
0
1
0
Order By: Relevance
“…However, due to the language gap between source and target languages, the teacher network that only accesses the ground-truth labels of the source language inevitably infers low-quality (noisy) pseudo labels for the target language. If these noisy pseudo labels are directly utilized for knowledge distillation, they will mislead the training process of the student network, resulting in negative knowledge transfer (Feng et al 2021). Only a few works have focused on this issue.…”
Section: Introductionmentioning
confidence: 99%
“…However, due to the language gap between source and target languages, the teacher network that only accesses the ground-truth labels of the source language inevitably infers low-quality (noisy) pseudo labels for the target language. If these noisy pseudo labels are directly utilized for knowledge distillation, they will mislead the training process of the student network, resulting in negative knowledge transfer (Feng et al 2021). Only a few works have focused on this issue.…”
Section: Introductionmentioning
confidence: 99%