CLMar 15, 2016

Multichannel Variable-Size Convolution for Sentence Classification

arXiv:1603.04513v1162 citations
Originality Incremental advance
AI Analysis

This work addresses sentence classification for NLP applications, but it is incremental as it builds on existing CNN and embedding methods.

The authors tackled sentence classification by proposing MVCNN, a CNN architecture that combines diverse pretrained word embeddings and extracts multigranular phrase features with variable-size convolution filters, achieving state-of-the-art performance on four tasks including sentiment prediction and subjectivity classification.

We propose MVCNN, a convolution neural network (CNN) architecture for sentence classification. It (i) combines diverse versions of pretrained word embeddings and (ii) extracts features of multigranular phrases with variable-size convolution filters. We also show that pretraining MVCNN is critical for good performance. MVCNN achieves state-of-the-art performance on four tasks: on small-scale binary, small-scale multi-class and largescale Twitter sentiment prediction and on subjectivity classification.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes