Work

Multichannel Variable-Size Convolution for Sentence Classification

Year: 2015

Type: conference-paper

Abstract: 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.

Source: Conference on Computational Natural Language Learning

DOI: 10.18653/v1/k15-1021

Authors: Wenpeng Yin, Hinrich Schütze

Institution: Ludwig-Maximilians-Universität München

Language: English

Topic: Sentiment Analysis and Opinion Mining

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Baidu, Deutsche Forschungsgemeinschaft

Award: G4777761225