2017/12/19 by Rasoul Kaljahi, Kaljahi, Rasoul, Jennifer Foster +1
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Sentiment Analysis and Opinion Mining
paper · pdf · doi:10.48550/arxiv.1712.07004
Any-gram kernels are a flexible and efficient way to employ bag-of-n-gram\nfeatures when learning from textual data. They are also compatible with the use\nof word embeddings so that word similarities can be accounted for. While the\noriginal any-gram kernels are implemented on top of tree kernels, we propose a\nnew approach which is independent of tree kernels and is more efficient. We\nalso propose a more effective way to make use of word embeddings than the\noriginal any-gram formulation. When applied to the task of sentiment\nclassification, our new formulation achieves significantly better performance.\n