Format:
1 Online-Ressource (367 pages)
ISBN:
9783642414916
Series Statement:
Lecture Notes in Computer Science / Lecture Notes in Artificial Intelligence v.8202
Content:
Preface -- Organization -- Table of Contents -- Word Segmentation -- Improving Chinese Word Segmentation Using Partially Annotated Sentences -- 1 Introduction -- 2 Learning with Partially Annotated Data -- 2.1 Partially Annotated Data as Training Data -- 2.2 Perpectron Algorithm for Partially Annotated Data -- 2.3 Self-training with Partially Annotated Data -- 2.4 Distributed Learning for Large-Scale Training Data -- 3 Partially Annotated Sentences for Chinese Word Segmentation -- 3.1 Agreement between Span Sets -- 3.2 Partially Annotated Sentences from Heterogeneous Segmented -- 3.3 Partially Annotated Sentences from Wikitexts -- 3.4 Mixed Training Data -- 4 Related Work -- 5 Experiments -- 5.1 Supervised Learning with Partially Annotated Data -- 5.2 Self-training with Partially Annotated Data -- 5.3 Distributed Learning with Large Data -- 6 Discussion and Conclusion -- References -- Chinese Natural Chunk Research Based on Natural Annotations in Massive Scale Corpora Exploring Work on Natural Chunk Recognition Using Explicit Boundary Indicators -- 1 Introduction -- 2 Language Computing Based on Natural Annotated Boundary Knowledge -- 3 Chinese "Natural Chunk" -- 4 Natural Chunk Recognition in Massive Scale Corpora -- 4.1 Natural Annotations with Distinctive Boundary Information -- 4.2 Natural Chunk Boundary Modeling -- 4.3 Evaluation of Natural Chunk Recognition -- 5 Experiments -- 5.1 Corpus and Dataset -- 5.2 Lexicon Knowledge in BICs -- 5.3 Word Segmentation Experiments with explicit BICs -- 5.4 Results and Analysis -- 6 Summary and Future Work -- References -- A Kalman Filter Based Human-Computer Interactive Word Segmentation System for Ancient Chinese Texts -- 1 Introduction -- 2 Related Work -- 3 Statistical Model -- 3.1 Baseline Model -- 3.2 Improved Statistical Model -- 3.3 Structural Words Optimization -- 4 Kalman Filter Model
Content:
4.1 Process State -- 4.2 Measurements and States Update -- 5 Human-Computer Interactive System -- 6 Experiments -- 6.1 Improved Statistical Model -- 6.2 Kalman Filter Model -- 7 Conclusions and Future Work -- References -- Chinese Word Segmentation with Character Abstraction -- 1 Introduction -- 2 Related Works -- 3 Discriminative Character-Based Word Segmentation -- 4 Character Abstraction: Learning Character Semantic Concepts -- 4.1 Semi-supervised K-means Cluster -- 5 Experiments -- 5.1 Dataset -- 5.2 Analysis -- 6 Conclusion -- References -- A Refined HDP-Based Model for Unsupervised Chinese Word Segmentation -- 1 Introduction -- 2 HDP-Based Unsupervised Word Segmentation -- 3 Refined Model -- 3.1 Improved Base Measure -- 3.2 Initial State -- 4 Experiment -- 4.1 Prior Knowledge Used -- 4.2 Model Selection -- 4.3 Experiment Result -- 5 Conclusion -- References -- Enhancing Chinese Word Segmentation with Character Clustering -- 1 Introduction -- 2 Character-Based Brown Clustering -- 2.1 Brown Clustering -- 2.2 Unigram Character Clustering -- 2.3 Bigram and Trigram Character Clustering -- 3 Semi-supervised Learning Model -- 3.1 Baseline Features -- 3.2 Mutual Information Features -- 3.3 Clustering Features -- 4 Experiments -- 4.1 Settings -- 4.2 Results -- 5 Conclusion and Future Work -- References -- Integrating Multi-source Bilingual Information for Chinese Word Segmentation in Statistical Machine Translation -- 1 Introduction -- 2 Producing the Set of Alternative -- 2.1 PreviousWork on Monolingual CWS -- 2.2 Combination of CWS Systems -- 3 Joint Translation Model for Integrating Multi-source Bilingual Information -- 3.1 Word-Based TranslationModel -- 3.2 English-Chinese Phrase-Based Named Entity TransliterationModel -- 3.3 Integrating the Information of Dictionary -- 4 Iterative Algorithm -- 5 Experiment Setup -- 5.1 Data Set and Evaluation
Content:
5.2 Baseline System and Translation System -- 6 Experiment -- 6.1 Segmentation Performance on Training Data Set -- 6.2 Translation Performance on Task IWSLT -- 7 Conclusion and Future Work -- References -- Open-Domain Q&A -- Interactive Question Answering Based on FAQ -- 1 Introduction -- 2 Related Work -- 3 Context Question Answering in Interactive Question Answering -- 3.1 Support Vector Based Ranking Learning Method -- 3.2 The Features for Context Question Answering -- 3.3 Context Features -- The Interaction between QA System and User -- 5 Experiment -- 6 Conclusions -- References -- Discourse, Coreference and Pragmatics -- Document Oriented Gap Filling of Definite Null Instantiation in FrameNet -- 1 Introduction -- 2 Related Work -- 3 Model for Gap Filling of DNI -- 3.1 Selection of Candidate Words Set -- 3.2 Features Description -- 3.3 Maximum Entropy Models -- 4 System Output and Evaluation -- 4.1 Corpus -- 4.2 Evaluation Measures -- 4.3 Result in Gold Standard Annotated Corpus -- 4.4 Result in NIs only Task Test Data -- 5 Conclusion and Further Work -- References -- Interesting Linguistic Features in Coreference Annotation of an Inflectional Language -- 1 Introduction -- 2 Mentions and Coreference Clusters -- 3 Related Work -- 4 Near-Identity -- 5 Dominant Expressions -- 6 Semantic Heads -- 7 Zero Subjects -- 8 Pronominal Coreference and Other Issues -- 9 Inter-Annotator Agreement -- 10 Conclusions and Perspectives -- References -- Statistical and Machine Learning Methods in NLP -- Semi-supervised Learning with Transfer Learning -- 1 Introduction -- 2 Transfer Progressive Transductive Support Vector Machine -- 3 Analysis -- 4 Experiment -- 4.1 Data Sets -- 4.2 Comparison Methods -- 4.3 Experiment Results -- 5 Conclusion -- References -- Online Distributed Passive-Aggressive Algorithm for Structured Learning -- 1 Introduction
Content:
2 Online Passive-Aggressive Algorithm -- 3 Distributed Implementation of Online Passive-Aggressive Algorithm -- 3.1 Parameters Averaging Strategy -- 4 Theoretical Analysis -- 5 Experiments -- 5.1 Experimental Discussion -- 6 Related Works -- 7 Conclusion -- References -- Power Law for Text Categorization -- 1 Introduction -- 2 Related Work -- 3 Re-examination of Power Law -- 3.1 Corpora -- 3.2 Token Frequency Distribution -- 3.3 Potential Useless Feature -- 4 Random Sampling Ensemble Bayesian Algorithm -- 4.1 Token Level Memory -- 4.2 Random Sampling Learning -- 4.3 Ensemble Bayesian Predicting -- 4.4 Space-Time Complexity -- 5 Experiment -- 5.1 Implementation -- 5.2 Task and Evaluation -- 5.3 Results and Discussions -- 6 Conclusion -- References -- Semantics -- Natural Language Understanding for Grading Essay Questions in Persian Language -- 1 Introduction -- 2 Syntactic Representation Methods -- 2.1 Phrase Structure -- 2.2 Grammar Representation Based on the Dependency -- 2.3 Comparison of Methods -- 3 Evaluation System of Users' Answers -- 4 Recommended Method -- 5 Procedures of Converting Texts into Objects -- 5.1 Generation of Initial Objects -- 6 Receiving the Answers and Evaluation -- 7 Persian Language and Investigation of System Stages -- 8 Conclusion and Future Work -- References -- Text Mining, Open-Domain Information Extraction and Machine Reading of the Web -- Learning to Extract Attribute Values from a Search Engine with Few Examples -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Candidate Value Detector -- 3.2 Attribute Value Classifier -- 3.3 Voter -- 4 Experiment -- 4.1 Evaluation Dataset -- 4.2 Experimental Results -- 4.3 Single Site -- 4.4 Comparison to a Previous System -- 4.5 Impact of the Amount of Annotated Data -- 5 Conclusions -- References -- User-Characteristics Topic Model -- 1 Introduction
Content:
2 User-Characteristics Topic Model -- 2.1 Motivation -- 2.2 Description of User-Characteristics LDA(UC-LDA) -- 2.3 Inference -- 2.4 UC-TagLDA -- 3 Experiments -- 3.1 Dataset -- 3.2 Perplexity -- 3.3 Word Distributions over Different Characteristics -- 3.4 Application on Recommendation(UC-TagLDA Only) -- 4 Conclusions -- References -- Mining User Preferences for Recommendation: A Competition Perspective -- 1 Introduction -- 2 Related Work -- 3 The User Preferences Mining Approach Based on Pairwise Comparisons for Recommendation -- 3.1 Motivation Discussion -- 3.2 Model Description -- 4 Experiments -- 4.1 Recommendation Effect Experiments -- 4.2 The Relationship between Competitive Scales and Recommendation Effect -- 5 Conclusions -- References -- Sentiment Analysis, Opinion Mining and Text Classification -- A Classification-Based Approach for Implicit Feature Identification -- 1 Introduction -- 2 Related Work -- 3 Classification-Based Approach -- 3.1 Problem Statement -- 3.2 Overview of the Approach -- 3.3 Explicit Feature-Opinion Pair Extraction -- 3.4 Feature-Opinion Pair Training Document Construction -- 3.5 Implicit Feature Identification -- 4 Experiments -- 4.1 Date Sets and Evaluation Measures -- 4.2 Evaluation of Explicit Feature-Opinion Pair Extraction -- 4.3 Evaluation of Implicit Future Identification -- 5 Conclusion and Feature Work -- References -- Role of Emoticons in Sentence-Level Sentiment Classification -- 1 Introduction -- 2 Related Work -- 3 Sentence-Level Sentiment Classification -- 4 Experiments and Results -- 5 Conclusion and Future Work -- References -- Emotional McGurk Effect? A Cross-Cultural Investigation on Emotion Expression under Vocal and Facial Conflict -- 1 Introduction -- 2 Perceptual Experiment on Cross-Cultural Emotion -- 3 Results and Analysis -- 3.1 Comparison on Perceptual Patterns
Content:
3.2 Comparison of Perceptual Patterns between Chinese and Japanese for Conflicting Stimuli
Additional Edition:
9783642414909
Additional Edition:
Erscheint auch als Druck-Ausgabe Sun, Maosong Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data : 12th China National Conference, CCL 2013 and First International Symposium, NLP-NABD 2013, Suzhou, China, October 10-12, 2013, Proceedings Berlin/Heidelberg : Springer Berlin Heidelberg,c2013 9783642414909
Language:
English
URL:
Volltext
(lizenzpflichtig)
Bookmarklink
