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.

[1]  Avrim Blum,et al.  Learning from Labeled and Unlabeled Data using Graph Mincuts , 2001, ICML.

[2]  Ruslan Salakhutdinov,et al.  Revisiting Semi-Supervised Learning with Graph Embeddings , 2016, ICML.

[3]  Dragomir R. Radev,et al.  Centroid-based summarization of multiple documents , 2004, Inf. Process. Manag..

[4]  Eduard H. Hovy,et al.  Recursive Deep Models for Discourse Parsing , 2014, EMNLP.

[5]  Mohamed Abdel Fattah A hybrid machine learning model for multi-document summarization , 2013, Applied Intelligence.

[6]  Xiaolong Wang,et al.  Automatic Text Summarization Based on Lexical Chains , 2005, ICNC.

[7]  Kathleen McKeown,et al.  Content Selection in Deep Learning Models of Summarization , 2018, EMNLP.

[8]  Bernhard Schölkopf,et al.  Cluster Kernels for Semi-Supervised Learning , 2002, NIPS.

[9]  Akitoshi Okumura,et al.  Hybrid Text Summarization Method based on the TF Method and the Lead Method , 2001, NTCIR.

[10]  Mahmoud Al-Ayyoub,et al.  Deep learning for Arabic NLP: A survey , 2017, J. Comput. Sci..

[11]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[12]  David A. Landgrebe,et al.  The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon , 1994, IEEE Trans. Geosci. Remote. Sens..

[13]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[14]  Min Zhang,et al.  Automatic online news issue construction in web environment , 2008, WWW.

[15]  Ryan P. Browne,et al.  Model-Based Learning Using a Mixture of Mixtures of Gaussian and Uniform Distributions , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Christian R. Huyck,et al.  Generating discourse structures for written texts , 2004, COLING 2004.

[17]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[18]  Danushka Bollegala,et al.  A Semi-Supervised Approach to Improve Classification of Infrequent Discourse Relations Using Feature Vector Extension , 2010, EMNLP.

[19]  Quoc V. Le,et al.  Semi-supervised Sequence Learning , 2015, NIPS.

[20]  Donald E. Knuth,et al.  Semantics of context-free languages , 1968, Mathematical systems theory.

[21]  Shafiq R. Joty,et al.  Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis , 2013, ACL.

[22]  Daniel Marcu,et al.  The rhetorical parsing, summarization, and generation of natural language texts , 1998 .

[23]  W. Mann,et al.  Rhetorical Structure Theory: looking back and moving ahead , 2006 .

[24]  Wenpeng Yin,et al.  Optimizing Sentence Modeling and Selection for Document Summarization , 2015, IJCAI.

[25]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[26]  Dan Klein,et al.  Jointly Learning to Extract and Compress , 2011, ACL.

[27]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[28]  Maxime Peyrard,et al.  A Simple Theoretical Model of Importance for Summarization , 2018, ACL.

[29]  Graeme Hirst,et al.  Text-level Discourse Parsing with Rich Linguistic Features , 2012, ACL.

[30]  Yu-Feng Li,et al.  Safe semi-supervised learning: a brief introduction , 2019, Frontiers of Computer Science.

[31]  Jason Weston,et al.  Deep learning via semi-supervised embedding , 2008, ICML '08.

[32]  Masaaki Nagata,et al.  Single-Document Summarization as a Tree Knapsack Problem , 2013, EMNLP.

[33]  Zhi-Hua Zhou,et al.  Ensemble Methods: Foundations and Algorithms , 2012 .

[34]  Jason Weston,et al.  Semi-supervised Protein Classification Using Cluster Kernels , 2003, NIPS.

[35]  Kam-Fai Wong,et al.  Extractive Summarization Using Supervised and Semi-Supervised Learning , 2008, COLING.

[36]  Maite Taboada,et al.  A Syntactic and Lexical-Based Discourse Segmenter , 2009, ACL.

[37]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[38]  Mirella Lapata,et al.  Neural Summarization by Extracting Sentences and Words , 2016, ACL.

[39]  Chun Zhang,et al.  Semi-Supervised Learning by Local Behavioral Searching Strategy , 2014 .

[40]  Martial Hebert,et al.  Semi-Supervised Self-Training of Object Detection Models , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[41]  Zhi-Hua Zhou,et al.  Semi-Supervised Regression with Co-Training , 2005, IJCAI.

[42]  Ali Ghodsi,et al.  Semi-Supervised Representation Learning based on Probabilistic Labeling , 2016, ArXiv.

[43]  Regina Barzilay,et al.  Using Lexical Chains for Text Summarization , 1997 .

[44]  Zoubin Ghahramani,et al.  Graph Kernels by Spectral Transforms , 2006, Semi-Supervised Learning.

[45]  Benoit Favre,et al.  A Scalable Global Model for Summarization , 2009, ILP 2009.

[46]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[47]  Latifur Khan,et al.  SISC: A Text Classification Approach Using Semi Supervised Subspace Clustering , 2009, 2009 IEEE International Conference on Data Mining Workshops.

[48]  William C. Mann,et al.  Rhetorical Structure Theory: Toward a functional theory of text organization , 1988 .

[49]  Jacob Eisenstein,et al.  Representation Learning for Text-level Discourse Parsing , 2014, ACL.

[50]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[51]  Luke S. Zettlemoyer,et al.  Human-in-the-Loop Parsing , 2016, EMNLP.

[52]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[53]  Zhen Wang,et al.  Knowledge Graph Embedding by Translating on Hyperplanes , 2014, AAAI.

[54]  Sergey Levine,et al.  Generalizing Skills with Semi-Supervised Reinforcement Learning , 2016, ICLR.

[55]  Chuanqing Wang,et al.  Attributed Rhetorical Structure Grammar for Domain Text Summarization , 2019, ArXiv.

[56]  Zhi-Hua Zhou,et al.  When semi-supervised learning meets ensemble learning , 2009, MCS.

[57]  Yihao Zhang,et al.  Semi-supervised hybrid clustering by integrating Gaussian mixture model and distance metric learning , 2013, Journal of Intelligent Information Systems.

[58]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[59]  Thorsten Joachims,et al.  Transductive Support Vector Machines , 2006, Semi-Supervised Learning.

[60]  Maosong Sun,et al.  Semi-Supervised Learning for Neural Machine Translation , 2016, ACL.

[61]  Alexander Kolesnikov,et al.  Revisiting Self-Supervised Visual Representation Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[62]  Ani Nenkova,et al.  Discourse indicators for content selection in summarization , 2010, SIGDIAL Conference.

[63]  Noah A. Smith,et al.  Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2016, ACL 2016.

[64]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[65]  Mohammad Reza Keyvanpour,et al.  Customers Behavior Modeling by Semi-Supervised Learning in Customer Relationship Management , 2012, ArXiv.

[66]  Nick Cramer,et al.  Automatic Keyword Extraction from Individual Documents , 2010 .

[67]  Christopher D. Manning,et al.  Effect of Non-linear Deep Architecture in Sequence Labeling , 2013, IJCNLP.

[68]  Jason Weston,et al.  A Neural Attention Model for Abstractive Sentence Summarization , 2015, EMNLP.

[69]  Yu Huang,et al.  Holographic Lexical Chain and Its Application in Chinese Text Summarization , 2017, APWeb/WAIM.

[70]  Shih-Fu Chang,et al.  Graph construction and b-matching for semi-supervised learning , 2009, ICML '09.

[71]  Ryan T. McDonald A Study of Global Inference Algorithms in Multi-document Summarization , 2007, ECIR.

[72]  Mitsuru Ishizuka,et al.  HILDA: A Discourse Parser Using Support Vector Machine Classification , 2010, Dialogue Discourse.

[73]  Matt J. Kusner,et al.  From Word Embeddings To Document Distances , 2015, ICML.

[74]  Zhi-Hua Zhou,et al.  Semi-supervised learning by disagreement , 2010, Knowledge and Information Systems.

[75]  O. Chapelle,et al.  Semi-Supervised Learning (Chapelle, O. et al., Eds.; 2006) [Book reviews] , 2009, IEEE Transactions on Neural Networks.

[76]  Peng Zhang,et al.  A neural translating general hyperplane for knowledge graph embedding , 2019, J. Comput. Sci..

[77]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[78]  Vishal Gupta,et al.  Recent automatic text summarization techniques: a survey , 2016, Artificial Intelligence Review.

[79]  Daniel Marcu,et al.  Sentence Level Discourse Parsing using Syntactic and Lexical Information , 2003, NAACL.

[80]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[81]  Zhiyuan Liu,et al.  Learning Entity and Relation Embeddings for Knowledge Graph Completion , 2015, AAAI.

[82]  Canhasi Ercan Graph-based models for multi-document summarization , 2014 .