Live and learn from mistakes: A lightweight system for document classification

Borodin, Yevgen; Polishchuk, Valentin; Mahmud, Jalal; Ramakrishnan, I. V.; Stent, Amanda

doi:10.1016/j.ipm.2012.02.001

Cited by 3 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A simple way to implement a tessellation of the feature space is by adopting a prototype based method. In particular, we focus on centroids as they have been successfully used in the text categorization literature and are generating a renewed interest in the last years due to their computational efficiency (Tan et al, 2011;Pang and Jiang, 2013;Wang et al, 2013a;Borodin et al, 2013). Tan (2008) reports significant improvements on naive Bayes and KNN methods using adaptive centroid classifiers in text categorization tasks.…”

Section: Multi-label Text Classificationmentioning

confidence: 99%

“…An online extension of this method has been formerly presented in (Tan et al, 2011) but applied to classic train/test problems where the method slightly outperforms SVMs. Recently, a similar technique was presented in (Borodin et al, 2013) for text classification in data stream environments. Unfortunately it focuses on single label classification and documents are represented using batch TF-IDF.…”

Section: Multi-label Text Classificationmentioning

confidence: 99%

“…An online extension of this procedure has been presented in (Tan et al, 2011) and applied to large train/test problems where the method slightly outperforms SVMs. A similar technique was presented in (Borodin et al, 2013) for text classification in stationary and non-stationary environments. Wang et al (2013a) propose to filter out instances far from the boundary to enhance the predictive power of CC and Pang and Jiang (2013) integrate it with a clustering algorithm to obtain a lightweight approximation of nearest neighbors.…”

Section: Additional Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Efficient classification of multi-labeled text streams by clashing

Ñanculef

Flaounas

Cristianini

2014

Expert Systems with Applications

View full text Add to dashboard Cite

We present a method for the classification of multi-labelled text documents explicitly designed for data stream applications that require to process a virtually infinite sequence of data using constant memory and constant processing time.Our method is composed of an online procedure used to efficiently map text into a low-dimensional feature space and a partition of this space into a set of regions for which the system extracts and keeps statistics used to predict multi-label text annotations. Documents are fed into the system as a sequence of words, mapped to a region of the partition, and annotated using the statistics computed from the labelled instances colliding in the same region. This approach is referred to as clashing.We illustrate the method in real-world text data, comparing the results with those obtained using other text classifiers. In addition, we provide an analysis about the effect of the representation space dimensionality on the predictive performance of the system. Our results show that the online embedding indeed approximates the geometry of the full corpus-wise TF and TF-IDF space. The model obtains competitive F measures with respect to the most accurate methods, using significantly fewer computational resources. In addition, the method achieves a higher macro-averaged F measure than methods with similar running time. Furthermore, the system is able to learn faster than the other methods from partially labelled streams.

show abstract