Natural Language Understanding and Intelligent Applications : 5th CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2016, and 24th International Conference on Computer Processing of Oriental Languages, ICCPOL 2016, Kunming, China,

This book constitutes the joint refereed proceedings of the 5th CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2016, and the 24th International Conference on Computer Processing of Oriental Languages, ICCPOL 2016, held in Kunming, China, in December 2016. The 48 revised full papers presented together with 41 short papers were carefully reviewed and selected from 216 submissions. The papers cover fundamental research in language computing, multi-lingual access, web mining/text mining, machine learning for NLP, knowledge graph, NLP for social network, as well as applications in language computing. Front Matter....Pages I-XXII Front Matter....Pages 1-1 Integrating Structural Context with Local Context for Disambiguating Word Senses....Pages 3-15 Tibetan Multi-word Expressions Identification Framework Based on News Corpora....Pages 16-26 Building Powerful Dependency Parsers for Resource-Poor Languages....Pages 27-38 Bidirectional Long Short-Term Memory with Gated Relevance Network for Paraphrase Identification....Pages 39-50 Syntactic Categorization and Semantic Interpretation of Chinese Nominal Compounds....Pages 51-62 TDSS: A New Word Sense Representation Framework for Information Retrieval....Pages 63-75 A Word Vector Representation Based Method for New Words Discovery in Massive Text....Pages 76-88 Front Matter....Pages 89-89 Better Addressing Word Deletion for Statistical Machine Translation....Pages 91-102 A Simple, Straightforward and Effective Model for Joint Bilingual Terms Detection and Word Alignment in SMT....Pages 103-115 Bilingual Parallel Active Learning Between Chinese and English....Pages 116-128 Study on the English Corresponding Unit of Chinese Clause....Pages 129-140 Research for Uyghur-Chinese Neural Machine Translation....Pages 141-152 MaxSD: A Neural Machine Translation Evaluation Metric Optimized by Maximizing Similarity Distance....Pages 153-161 Automatic Long Sentence Segmentation for Neural Machine Translation....Pages 162-174 Front Matter....Pages 175-175 Topic Segmentation of Web Documents with Automatic Cue Phrase Identification and BLSTM-CNN....Pages 177-188 Multi-task Learning for Gender and Age Prediction on Chinese Microblog....Pages 189-200 Dropout Non-negative Matrix Factorization for Independent Feature Learning....Pages 201-212 Analysing the Semantic Change Based on Word Embedding....Pages 213-223 Learning Word Sense Embeddings from Word Sense Definitions....Pages 224-235 Front Matter....Pages 237-237 Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition....Pages 239-250 Front Matter....Pages 237-237 Improving First Order Temporal Fact Extraction with Unreliable Data....Pages 251-262 Reducing Human Effort in Named Entity Corpus Construction Based on Ensemble Learning and Annotation Categorization....Pages 263-274 A Convolution BiLSTM Neural Network Model for Chinese Event Extraction....Pages 275-287 Detection of Entity Mixture in Knowledge Bases Using Hierarchical Clustering....Pages 288-299 Knowledge Base Question Answering Based on Deep Learning Models....Pages 300-311 An Open Domain Topic Prediction Model for Answer Selection....Pages 312-323 Joint Event Extraction Based on Skip-Window Convolutional Neural Networks....Pages 324-334 Improving Collaborative Filtering with Long-Short Interest Model....Pages 335-346 Front Matter....Pages 347-347 Leveraging Hierarchical Deep Semantics to Classify Implicit Discourse Relations via Mutual Learning Method....Pages 349-359 Transition-Based Discourse Parsing with Multilayer Stack Long Short Term Memory....Pages 360-373 Predicting Implicit Discourse Relation with Multi-view Modeling and Effective Representation Learning....Pages 374-386 A CDT-Styled End-to-End Chinese Discourse Parser....Pages 387-398 Front Matter....Pages 399-399 Events Detection and Temporal Analysis in Social Media....Pages 401-412 Discovering Concept-Level Event Associations from a Text Stream....Pages 413-424 A User Adaptive Model for Followee Recommendation on Twitter....Pages 425-436 Who Will Tweet More? Finding Information Feeders in Twitter....Pages 437-448 Front Matter....Pages 449-449 Discrete and Neural Models for Chinese POS Tagging: Comparison and Combination....Pages 451-460 Improving Word Vector with Prior Knowledge in Semantic Dictionary....Pages 461-469 Adapting Attention-Based Neural Network to Low-Resource Mongolian-Chinese Machine Translation....Pages 470-480 Sentence Similarity on Structural Representations....Pages 481-488 Front Matter....Pages 449-449 Word Sense Disambiguation Using Context Translation....Pages 489-496 Cyrillic Mongolian Named Entity Recognition with Rich Features....Pages 497-505 Purchase Prediction via Machine Learning in Mobile Commerce....Pages 506-513 Exploring Long Tail Data in Distantly Supervised Relation Extraction....Pages 514-522 Detecting Potential Adverse Drug Reactions from Health-Related Social Networks....Pages 523-530 Iterative Integration of Unsupervised Features for Chinese Dependency Parsing....Pages 531-540 Can We Neglect Function Words in Word Embedding?....Pages 541-548 A Similarity Algorithm Based on the Generality and Individuality of Words....Pages 549-558 An Improved Information Gain Algorithm Based on Relative Document Frequency Distribution....Pages 559-567 Finding the True Crowds: User Filtering in Microblogs....Pages 568-574 Learning to Recognize Protected Health Information in Electronic Health Records with Recurrent Neural Network....Pages 575-582 Sentiment Classification of Social Media Text Considering User Attributes....Pages 583-594 Learning from User Feedback for Machine Translation in Real-Time....Pages 595-607 GuideRank: A Guided Ranking Graph Model for Multilingual Multi-document Summarization....Pages 608-620 Fast-Syntax-Matching-Based Japanese-Chinese Limited Machine Translation....Pages 621-630 Value at Risk for Risk Evaluation in Information Retrieval....Pages 631-638 Chinese Paraphrases Acquisition Based on Random Walk N Step....Pages 639-647 A Micro-topic Model for Coreference Resolution Based on Theme-Rheme Structure....Pages 648-656 Learning from LDA Using Deep Neural Networks....Pages 657-664 Relation Classification: CNN or RNN?....Pages 665-675 Front Matter....Pages 677-677 Ensemble of Feature Sets and Classification Methods for Stance Detection....Pages 679-688 Exploiting External Knowledge and Entity Relationship for Entity Search....Pages 689-700 A Flexible and Sentiment-Aware Framework for Entity Search....Pages 701-710 Word Segmentation on Micro-Blog Texts with External Lexicon and Heterogeneous Data....Pages 711-721 Open Domain Question Answering System Based on Knowledge Base....Pages 722-733 Recurrent Neural Word Segmentation with Tag Inference....Pages 734-743 Chinese Word Similarity Computing Based on Combination Strategy....Pages 744-752 An Empirical Study on Chinese Microblog Stance Detection Using Supervised and Semi-supervised Machine Learning Methods....Pages 753-765 Combining Word Embedding and Semantic Lexicon for Chinese Word Similarity Computation....Pages 766-777 Football News Generation from Chinese Live Webcast Script....Pages 778-789 Convolutional Deep Neural Networks for Document-Based Question Answering....Pages 790-797 Research on Summary Sentences Extraction Oriented to Live Sports Text....Pages 798-807 Front Matter....Pages 809-809 Statistical Entity Ranking with Domain Knowledge....Pages 811-818 Study on the Method of Precise Entity Search Based on Baidu’s Query....Pages 819-827 Overview of the NLPCC-ICCPOL 2016 Shared Task: Chinese Word Similarity Measurement....Pages 828-839 Exploring Various Linguistic Features for Stance Detection....Pages 840-847 Overview of Baidu Cup 2016: Challenge on Entity Search....Pages 848-853 A Feature-Rich CRF Segmenter for Chinese Micro-Blog....Pages 854-861 NLPCC 2016 Shared Task Chinese Words Similarity Measure via Ensemble Learning Based on Multiple Resources....Pages 862-869 Overview of the NLPCC-ICCPOL 2016 Shared Task: Sports News Generation from Live Webcast Scripts....Pages 870-875 Front Matter....Pages 809-809 Sports News Generation from Live Webcast Scripts Based on Rules and Templates....Pages 876-884 A Deep Learning Approach for Question Answering Over Knowledge Base....Pages 885-892 Stance Detection in Chinese MicroBlogs with Neural Networks....Pages 893-900 Overview of the NLPCC-ICCPOL 2016 Shared Task: Chinese Word Segmentation for Micro-Blog Texts....Pages 901-906 Overview of NLPCC Shared Task 4: Stance Detection in Chinese Microblogs....Pages 907-916 Combining Deep Learning with Information Retrieval for Question Answering....Pages 917-925 A Hybrid Approach to DBQA....Pages 926-933 A Chinese Question Answering Approach Integrating Count-Based and Embedding-Based Features....Pages 934-941 Overview of the NLPCC-ICCPOL 2016 Shared Task: Open Domain Chinese Question Answering....Pages 942-948 Back Matter....Pages 949-952