Generalization of metric classification algorithms for sequences classification and labelling
This work addresses sequence classification and labeling tasks, but appears incremental as it modifies existing metric algorithms like k-NN for sequential data.
The authors tackled the problem of adapting metric classification algorithms for sequential data by proposing a generalization method and developing a new algorithm for classification and labeling, which they compared to CRF on the CoNLL2000 chunking dataset.
The article deals with the issue of modification of metric classification algorithms. In particular, it studies the algorithm k-Nearest Neighbours for its application to sequential data. A method of generalization of metric classification algorithms is proposed. As a part of it, there has been developed an algorithm for solving the problem of classification and labelling of sequential data. The advantages of the developed algorithm of classification in comparison with the existing one are also discussed in the article. There is a comparison of the effectiveness of the proposed algorithm with the algorithm of CRF in the task of chunking in the open data set CoNLL2000.