Classifier chains for multi-label classification

Read, Jesse; Pfahringer, Bernhard; Holmes, Geoff; Frank, Eibe

doi:10.1007/s10994-011-5256-5

Cited by 1,754 publications

(712 citation statements)

References 27 publications

Supporting

Mentioning

691

Contrasting

Unclassified

Order By: Relevance

“…We also plan to experiment with different algorithms to replace the various components of our framework. For our multi-label ranking component, various multi-label learning algorithms can be used to replace our proposed three methods, for example, LEAD [39] , class chain method [40] , could also be used. In the similarity-based ranking component, we can use different similarity metrics, for example, Euclidean distance, Minkowski distance [15] .…”

Section: Discussionmentioning

confidence: 99%

TagCombine: Recommending Tags to Contents in Software Information Sites

Wang

Xia

2015

J. Comput. Sci. Technol.

View full text Add to dashboard Cite

Nowadays, software engineers use a variety of online media to search and become informed of new and interesting technologies, and to learn from and help one another. We refer to these kinds of online media which help software engineers improve their performance in software development, maintenance, and test processes as software information sites. In this paper, we propose TagCombine, an automatic tag recommendation method which analyzes objects in software information sites. TagCombine has three different components: 1) multi-label ranking component which considers tag recommendation as a multi-label learning problem; 2) similarity-based ranking component which recommends tags from similar objects; 3) tag-term based ranking component which considers the relationship between different terms and tags, and recommends tags after analyzing the terms in the objects. We evaluate TagCombine on four software information sites, Ask Different, Ask Ubuntu, Freecode, and Stack Overflow. On averaging across the four projects, TagCombine achieves recall@5 and recall@10 to 0.619 8 and 0.762 5 respectively, which improves TagRec proposed by Al-Kofahi et al. by 14.56% and 10.55% respectively, and the tag recommendation method proposed by Zangerle et al. by 12.08% and 8.16% respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

TagCombine: Recommending Tags to Contents in Software Information Sites

Wang

Xia

2015

J. Comput. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Classifier chains methods are the closest to our work. They decompose the problem into multiple binary classification problems, one for each label [23]. This method assumes that instances are labeled with multiple classes.…”

Section: Related Workmentioning

confidence: 99%

Decision Mining Revisited - Discovering Overlapping Rules

Mannhardt

Leoni

Reijers

et al. 2016

Advanced Information Systems Engineering

View full text Add to dashboard Cite

“…Modeling label dependencies is widely acknowledged to be important for accurate classification in multi-label problems, yet has been problematic in the past for datasets with large numbers of labels, as summarized in Read et al (2009): The consensus view in the literature is that it is crucial to take into account label correlations during the classification process . .…”

Section: A Generative Modeling Approachmentioning

confidence: 99%

“…Most discriminative approaches to multi-label classification have employed some variant of the "binary problemtransformation" technique, in which the multi-label classification problem is transformed into a set of binary-classification problems, each of which can then be solved using a suitable binary classifier (Rifkin and Klautau 2004;Tsoumakas and Katakis 2007;Tsoumakas et al 2009;Read et al 2009). The most commonly employed method in the literature is the "onevs-all" transformation, in which C independent binary classifiers are trained-one classifier for each label.…”

Section: Related Workmentioning

confidence: 99%

Statistical topic models for multi-label document classification

et al. 2011

View full text Add to dashboard Cite

Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per document increase. This problem is amplified when the label frequencies exhibit the type of highly skewed distributions that are often observed in real-world datasets. In this paper we investigate a class of generative statistical topic models for multi-label documents that associate individual word tokens with different labels. We investigate the advantages of this approach relative to discriminative models, particularly with respect to classification problems involving large numbers of relatively rare labels. We compare the performance of generative and discriminative approaches on document labeling tasks ranging from datasets with several thousand labels to datasets with tens of labels. The experimental results indicate that probabilistic generative models can achieve competitive multi-label classification performance compared to discriminative methods, and have advantages for datasets with many labels and skewed label frequencies.

show abstract

Classifier chains for multi-label classification

Cited by 1,754 publications

References 27 publications

TagCombine: Recommending Tags to Contents in Software Information Sites

TagCombine: Recommending Tags to Contents in Software Information Sites

Decision Mining Revisited - Discovering Overlapping Rules

Statistical topic models for multi-label document classification

Contact Info

Product

Resources

About