Shengluan Hou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shengluan Hou has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Chaoqun Fei
2 shared publicationsRuqian Lu
Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
2 shared publications- Shu-Han Zhang
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
2 shared publications Shuhan Zhang
2 shared publications- Chao-Qun Fei
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
1 shared publication - Chaoqun Fei
Chinese Academy of Sciences
1 shared publication
Latest Publications
- 31 May 2021
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 36 (3) , 633-663
A Survey of Text Summarization Approaches Based on Deep Learning
- 31 May 2021
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 36 (3) , 633-663
A Survey of Text Summarization Approaches Based on Deep Learning
- 1 December 2020
- Published by Elsevier in Information Systems
- Vol. 94
Knowledge-guided unsupervised rhetorical parsing for text summarization
- 1 December 2020
- Published by Elsevier in Information Systems
- Vol. 94
Knowledge-guided unsupervised rhetorical parsing for text summarization
- 1 November 2020
- Published by Elsevier in Expert Systems with Applications
- Vol. 157
Rhetorical structure theory: A comprehensive review of theory, parsing methods and applications
- 1 November 2020
- Published by Elsevier in Expert Systems with Applications
- Vol. 157
Rhetorical structure theory: A comprehensive review of theory, parsing methods and applications
- Open Access
On Semi-Supervised Multiple Representation Behavior Learning
We propose a novel paradigm of semi-supervised learning (SSL)--the semi-supervised multiple representation behavior learning (SSMRBL). SSMRBL aims to tackle the difficulty of learning a grammar for natural language parsing where the data are natural language texts and the 'labels' for marking data are parsing trees and/or grammar rule pieces. We call such 'labels' as compound structured labels which require a hard work for training. SSMRBL is an incremental learning process that can learn more than one representation, which is an appropriate solution for dealing with the scarce of labeled training data in the age of big data and with the heavy workload of learning compound structured labels. We also present a typical example of SSMRBL, regarding behavior learning in form of a grammatical approach towards domain-based multiple text summarization (DBMTS). DBMTS works under the framework of rhetorical structure theory (RST). SSMRBL includes two representations: text embedding (for representing information contained in the texts) and grammar model (for representing parsing as a behavior). The first representation was learned as embedded digital vectors called impacts in a low dimensional space. The grammar model was learned in an iterative way. Then an automatic domain-oriented multi-text summarization approach was proposed based on the two representations discussed above. Experimental results on large-scale Chinese dataset SogouCA indicate that the proposed method brings a good performance even if only few labeled texts are used for training with respect to our defined automated metrics.
Open AccessOn Semi-Supervised Multiple Representation Behavior Learning
We propose a novel paradigm of semi-supervised learning (SSL)--the semi-supervised multiple representation behavior learning (SSMRBL). SSMRBL aims to tackle the difficulty of learning a grammar for natural language parsing where the data are natural language texts and the 'labels' for marking data are parsing trees and/or grammar rule pieces. We call such 'labels' as compound structured labels which require a hard work for training. SSMRBL is an incremental learning process that can learn more than one representation, which is an appropriate solution for dealing with the scarce of labeled training data in the age of big data and with the heavy workload of learning compound structured labels. We also present a typical example of SSMRBL, regarding behavior learning in form of a grammatical approach towards domain-based multiple text summarization (DBMTS). DBMTS works under the framework of rhetorical structure theory (RST). SSMRBL includes two representations: text embedding (for representing information contained in the texts) and grammar model (for representing parsing as a behavior). The first representation was learned as embedded digital vectors called impacts in a low dimensional space. The grammar model was learned in an iterative way. Then an automatic domain-oriented multi-text summarization approach was proposed based on the two representations discussed above. Experimental results on large-scale Chinese dataset SogouCA indicate that the proposed method brings a good performance even if only few labeled texts are used for training with respect to our defined automated metrics.
- 20 October 2018
- Published by Springer Nature
- p. 468-482
Cpriori: An Index-Based Framework to Extract the Generalized Center Strings
- 20 October 2018
- Published by Springer Nature
- p. 468-482
Cpriori: An Index-Based Framework to Extract the Generalized Center Strings
- 3 August 2017
- Published by Springer Nature
- p. 266-281
Holographic Lexical Chain and Its Application in Chinese Text Summarization
- 3 August 2017
- Published by Springer Nature
- p. 266-281
Holographic Lexical Chain and Its Application in Chinese Text Summarization