FSFP: Transfer Learning From Long Texts to the Short

Wei, Fengmei; Zhang, Jianpei; Chu, Yiyi; Yang, Jing

doi:10.12785/amis/080462

Cited by 17 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the current methods to alleviate the above problem is transfer learning, which has been obtained better results in web text data mining [4], document classification [5], [6]. The main idea of transfer learning is to utilize the knowledge from other domain(s) to help learn the current domain.…”

Section: Introductionmentioning

confidence: 99%

An Active Transfer Learning Framework for Protein-Protein Interaction Extraction

Zheng

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARY Protein-Protein Interaction Extraction (PPIE) from biomedical literatures is an important task in biomedical text mining and has achieved great success on public datasets. However, in real-world applications, the existing PPI extraction methods are limited to label effort. Therefore, transfer learning method is applied to reduce the cost of manual labeling. Current transfer learning methods suffer from negative transfer and lower performance. To tackle this problem, an improved TrAdaBoost algorithm is proposed, that is, relative distribution is introduced to initialize the weights of TrAdaBoost to overcome the negative transfer caused by domain differences. To make further improvement on the performance of transfer learning, an approach combining active learning with the improved TrAdaBoost is presented. The experimental results on publicly available PPI corpora show that our method outperforms TrAdaBoost and SVM when the labeled data is insufficient,and on document classification corpora, it also illustrates that the proposed approaches can achieve better performance than TrAdaBoost and TPTSVM in final, which verifies the effectiveness of our methods.

show abstract

Section: Introductionmentioning

confidence: 99%

An Active Transfer Learning Framework for Protein-Protein Interaction Extraction

Zheng

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…As Pan et al [1] suggested, TL is categorized as Inductive TL [2], [3] (where some labeled data is available in the target domain), Transductive TL [4] (where labeled data is only available in the source domain(s)), and Unsupervised TL [5] (where no labeled data is available in the source(s) and target domains). Inductive TL is the most intuitively appealing because it suggests that some data from the source domain(s) can be taken advantage of with the guidance of a few labeled data in the target domain.…”

Section: Introductionmentioning

confidence: 99%

Set-Based Boosting for Instance-Level Transfer on Multi-Classification

Yin¹,

Yang²,

Wang³

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Transfer boosting, a branch of instance-based transfer learning, is a commonly adopted transfer learning method. However, currently popular transfer boosting methods focus on binary classification problems even though there are many multi-classification tasks in practice. In this paper, we developed a new algorithm called MultiTransferBoost on the basis of TransferBoost for multi-classification. MultiTransferBoost firstly separated the multi-classification problem into several orthogonal binary classification problems. During each iteration, MultiTransferBoost boosted weighted instances from different source domains while each instance's weight was assigned and updated by evaluating the difficulty of the instance being correctly classified and the "transferability" of the instance's corresponding source domain to the target. The updating process repeated until it reached the predefined training error or iteration number. The weight update factors, which were analyzed and adjusted to minimize the Hamming loss of the output coding, strengthened the connections among the sub binary problems during each iteration. Experimental results demonstrated that MultiTransferBoost had better classification performance and less computational burden than existing instance-based algorithms using the One-Against-One (OAO) strategy.

show abstract