Bridging Domains Using World Wide Knowledge for Transfer Learning

Abstract

A major problem of classification learning is the lack of ground-truth labeled data. It is usually expensive to label new data instances for training a model. To solve this problem, domain adaptation in transfer learning has been proposed to classify target domain data by using some other source domain data, even when the data may have different distributions. However, domain adaptation may not work well when the differences between the source and target domains are large. In this paper, we design a novel transfer learning approach, called BIG (Bridging Information Gap), to effectively extract useful knowledge in a worldwide knowledge base, which is then used to link the source and target domains for improving the classification performance. BIG works when the source and target domains share the same feature space but different underlying data distributions. Using the auxiliary source data, we can extract a "bridge" that allows cross-domain text classification problems to be solved using standard semisupervised learning algorithms. A major contribution of our work is that with BIG, a large amount of worldwide knowledge can be easily adapted and used for learning in the target domain. We conduct experiments on several real-world cross-domain text classification tasks and demonstrate that our proposed approach can outperform several existing domain adaptation approaches significantly.

The People’s Encyclopedia Under the Gaze of the Sages: A Systematic Review of Scholarly Research on Wikipedia

“…They proposed a "solution for answer validation where answers returned by open-domain Question Answering Systems can be validated using online resources such as Wikipedia andGoogle" (2010, p.1935). Xiang et al (2010) proposed new algorithms for text analysis and retrieval to address the gap between different knowledge areas and transfer the knowledge from one domain to another one. Wikipedia was used as a supporting data source to assist the classification task using semisupervised learning.…”

A survey of machine learning for big data processing

“…However, with the data explosion from variety of sources, great heterogeneity of the collected data destroys the hypothesis. To tackle this issue, transfer learning has been proposed to allow the domains, tasks, and distributions to be different, which can extract knowledge from one or more source tasks and apply the knowledge to a target task [50,51]. The advantage of transfer learning is that it can intelligently apply knowledge learned previously to solve new problems faster.…”

Excavating the mother lode of human-generated text: A systematic review of research that uses the wikipedia corpus

“…They proposed an answer validation solution using various resources including Wikipedia to validate answers offered by "open-domain Question Answering Systems" [111, p.1935]. Xiang et al [136] proposed new approaches for text analysis and retrieval to address the gap between different knowledge areas and transfer the knowledge from one domain to another. The authors studied the knowledge gap between two domains and proposed a criteria to sample data from Wikipedia to fill this gap and then train a transductive SVM classifier on the augmented dataset.…”