CNN Architecture Predicting Movie Rating from Audience’s Reviews Written in Korean
1
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
In this paper, we present a movie rating prediction architecture based on a convolutional neural network (CNN). Our prediction architecture extends TextCNN, a popular CNN-based architecture for sentence classification, in three aspects. First, character embeddings are utilized to cover many variants of words since reviews are short and not well-written linguistically. Second, the attention mechanism (i.e., squeeze-and-excitation) is adopted to focus on important features. Third, a scoring function is proposed to convert the output of an activation function to a review score in a certain range (1-10). We evaluated our prediction architecture on a movie review dataset and achieved a low MSE (e.g., 3.3841) compared with an existing method. It showed the superiority of our movie rating prediction architecture.
Abstract
In this paper, we present a movie rating prediction architecture based on a convolutional neural network (CNN). Our prediction architecture extends TextCNN, a popular CNN-based architecture for sentence classification, in three aspects. First, character embeddings are utilized to cover many variants of words since reviews are short and not well-written linguistically. Second, the attention mechanism (i.e., squeeze-and-excitation) is adopted to focus on important features. Third, a scoring function is proposed to convert the output of an activation function to a review score in a certain range (1-10). We evaluated our prediction architecture on a movie review dataset and achieved a low MSE (e.g., 3.3841) compared with an existing method. It showed the superiority of our movie rating prediction architecture.
참고문헌 (19)
- A. Krizhevsky, "Advances in Neural Information Processing Systems", pp.1097~1105 (2012)
- O. Abdel-Hamid, "Convolutional neural networks for speech recognition", IEEE, 2014, pp.22(10), 1533~1545
- R. Collobert, "A unified architecture for natural language processing : Deep neural networks with multitask learning", Proceedings of the 25th Inter-National Conference on Machine Learning, pp.160~167 (2008)
- Y. Kim, "Convolutional Neural Networks for Sentence Classification", ArXiv e-prints : 1408. 5882, ~ (2014)
- K. Simonyan, "Very Deep Convolutional Networks for Large-Scale Image Recognition", ArXiv e-prints : 1409. 1556, ~ (2014)
- A. Conneau, "Very Deep Convolutional Networks for Text Classification", ArXiv eprints : 1606. 01781, ~ (2016)
- H. T. Le, "Do convolutional networks need to be deep for text classification?", arXiv preprint 1707. 04108, ~ (2017)
- C. M. Chang, "Changing models across cultures : Associations of phonological awareness and morphological structure awareness with vocabulary and word recognition in second graders from beijing, hong kong, korea, and the united states", Journal of Experimental Child Psychology, 92(2), pp.140~160 (2005)
- S. Petrov, "A universal part-ofspeech tagset", arXiv preprint arXiv : 1104. 2086, ~ (2011)
- "Mecab-ko morphological analyzer"[URL]
- "Twitter morphological analyzer"[URL]
- "Hannanum morphological analyzer"[URL]
- "KoNLPy benchmark performance among the libraries"[URL]
- J. Hu, "Squeezeand-Excitation Networks", ArXiv e-prints : 1709. 01507, ~ (2017)
- Ashish Vaswani, "Advances in Neural Information Processing Systems", pp.5998~6008 (2017)
- Devlin, J, "BERT:Pre-training of Deep Bidirectional Transformers for Language Understanding", arXiv preprint arXiv : 1810. 04805, ~ (2018)
- X. Yu, "general-purpose tagger with convolutional neural networks", arXiv preprint : 1706. 01723, ~ (2017)
- D. P. Kingma, "Adam : A Method for Stochastic Optimization", ArXiv e-prints, 1412.6980, ~ (2014)
- M. D. Zeiler, "Adadelta : an adaptive learning rate method", arXiv preprint : 1212. 5701, ~ (2012)