Multiview Convolutional Neural Networks for Multidocument Extractive Summarization
Authors:
- 28 November 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 47 (10) , 3230-3242
Abstract
Multidocument summarization has gained popularity in many real world applications because vital information can be extracted within a short time. Extractive summarization aims to generate a summary of a document or a set of documents by ranking sentences and the ranking results rely heavily on the quality of sentence features. However, almost all previous algorithms require hand-crafted features for sentence representation. In this paper, we leverage on word embedding to represent sentences so as to avoid the intensive labor in feature engineering. An enhanced convolutional neural networks (CNNs) termed multiview CNNs is successfully developed to obtain the features of sentences and rank sentences jointly. Multiview learning is incorporated into the model to greatly enhance the learning capability of original CNN. We evaluate the generic summarization performance of our proposed method on five Document Understanding Conference datasets. The proposed system outperforms the state-of-the-art approaches and the improvement is statistically significant shown by paired $t$-test.Keywords
This publication has 30 references indexed in Scilit:
- Deep learningNature, 2015
- #TagSpace: Semantic Embeddings from Hashtags2014
- Convolutional Neural Networks for Sentence Classification2014
- Semantic Parsing for Single-Relation Question Answering2014
- AN APPROACH FOR TEXT SUMMARIZATION USING DEEP LEARNING ALGORITHMJournal of Computer Science, 2014
- A survey of multi-view machine learningNeural Computing and Applications, 2013
- Multiview Metric Learning with Global Consistency and Local SmoothnessACM Transactions on Intelligent Systems and Technology, 2012
- Composite kernel learningMachine Learning, 2009
- Neural Probabilistic Language Models2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998