by Lam Sze-sing. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1995. / Includes bibliographical references (leaves 119-123). / Chapter CHAPTER 1 --- INTRODUCTION --- p.1 / Chapter 1.1 --- Introduction --- p.1 / Chapter 1.2 --- Statement of Thesis --- p.5 / Chapter 1.3 --- Organization of this Thesis --- p.6 / Chapter CHAPTER 2 --- RELATED WORK --- p.8 / Chapter 2.1 --- Overview --- p.8 / Chapter 2.2 --- Corpus-Based Knowledge Acquisition --- p.12 / Chapter 2.3 --- Linguistic-Based Knowledge Acquisition --- p.18 / Chapter 2.3.1 --- Knowledge Acquisition from Standard Dictionaries --- p.18 / Chapter 2.3.2 --- Knowledge Acquisition from Standard Thesauri --- p.23 / Chapter 2.4 --- Remarks --- p.24 / Chapter CHAPTER 3 --- A METHOD TO EXTRACT THE INTER-WORD SEMANTIC RELATIONSHIP FROM《同義詞詞林》 --- p.25 / Chapter 3.1 --- Background --- p.25 / Chapter 3.1.1 --- Structure of《《同義詞詞林》 --- p.26 / Chapter 3.1.2 --- Knowledge Representation of a Machine Tractable Thesaurus --- p.28 / Chapter 3.1.3 --- Extracting the Semantic Knowledge by Simple Co-occurrence --- p.28 / Chapter 3.2 --- Association Network --- p.31 / Chapter 3.3 --- Semantic Association Model --- p.33 / Chapter 3.3.1 --- Problems with the Simple Co-occurrence Method --- p.34 / Chapter 3.3.2 --- Methodology of Semantic Association Model --- p.39 / Chapter 3.4 --- Inter-word Semantic Function ..… --- p.51 / Chapter CHAPTER 4 --- NOUN-VERB-NOUN COMPOUND WORD DETECTION : AN EXPERIMENT --- p.55 / Chapter 4.1 --- Overview --- p.56 / Chapter 4.2 --- N-V-N Compound Word Detection Model --- p.61 / Chapter 4.3 --- Experimental Results of N-V-N Compound Word Detection --- p.63 / Chapter CHAPTER 5 --- WORD SENSE DISAMBIGUATION : AN APPLICATION … --- p.66 / Chapter 5.1 --- Overview --- p.67 / Chapter 5.2 --- Word-Sense Disambiguation Model --- p.72 / Chapter 5.2.1 --- Linguistic Resource --- p.72 / Chapter 5.2.2 --- The LSD-C Algorithm --- p.73 / Chapter 5.2.3 --- LSD-C in Action --- p.78 / Chapter 5.3 --- Experimental Results of Word Sense Disambiguation --- p.83 / Chapter CHAPTER 6 --- CONCLUSIONS & FURTHER RESEARCH --- p.93 / Chapter 6.1 --- Conclusions --- p.93 / Chapter 6.2 --- Further Research --- p.96 / Chapter 6.2.1 --- Enriching the Knowledge --- p.96 / Chapter 6.2.2 --- Enhancing the N-V-N Compound Word Detection Model --- p.98 / Chapter 6.2.3 --- Enhancing the LSD-C Algorithm --- p.99 / APPENDICES --- p.101 / Appendix A - Dependency Grammar --- p.101 / Appendix B - Sample Articles from a Local Chinese Newspaper --- p.104 / Appendix C - Ambiguous Words with the Senses Given by《現代漢語詞 典》 --- p.108 / Appendix D - List of Stop Words for the Testing Samples --- p.117 / REFERENCES --- p.119

O CleverCare é um framework para controle, gestão e orientação de pacientes que necessitam de acompanhamento médico contínuo. O sistema possui ferramentas de mineração de textos responsáveis por compreender o conteúdo das mensagens e integrar com serviços de mensagem para envio e recebimento das mesmas, onde inicia diálogos com o paciente para gerenciar atividades rotineiras personalizadas e permite, inclusive, ao paciente fazer perguntas a respeito de uma enfermidade ou condição clínica. Desta forma, a comunicação com o paciente é a base para o sucesso do CleverCare, o qual atualmente possui suporte para o português, atuando por meio de suporte e empoderando o paciente ao cuidado de sua saúde. Compreender as implicações lógicas e adaptações necessárias para a compreensão de textos em diferentes idiomas pode fornecer informações para a aplicação dos mesmos procedimentos a outros idiomas, correlacionando informações e estabelecendo lógicas para traduções e tratamento de termos específicos da área, permitindo atender a uma maior demanda de pacientes que necessitam de tratamento contínuo. Para o desenvolvimento do projeto foram utilizadas abordagens e técnicas visando a escalabilidade e expansão de idiomas de maneira dinâmica. Para isso além das decisões de alterações específicas do sistema foram utilizadas ferramentas como o NLTK para o aperfeiçoamento e realização das adaptações necessárias ao projeto, uma vez que essa ferramenta possui suporte a diversos idiomas e está em constante melhoria. Os resultados, analisados por meio de técnicas de acurácia, precisão e revocação, demonstram que a melhoria observada com as adaptações do sistema para suporte aos idiomas de interesse foram positivas e significativas, com aumento de 13% nos indicadores de revocação e acurácia e manutenção da precisão em 100%. Sendo assim, o CleverCare apresentou um bom desempenho e foi capaz de classificar corretamente as mensagens, permitindo ao sistema reconhecer e classificar corretamente diferentes idiomas. Esta solução permite ao sistema não apenas fazer o processamento de diálogos em português, inglês e espanhol, mas também ingressar no mercado internacional com a possibilidade de expansão e escalabilidade para outros idiomas / CleverCare is a framework for the control, management, and guidance of patients who need ongoing medical follow-up. The system has text-mining tools responsible for understanding the content of the messages and integrating with message services to send and receive messages, where it initiates dialogues with the patient to manage personalized routine activities and allows the patient to ask questions about them in relation to an illness or clinical condition. In this way, communication with the patient is the basis for the success of CleverCare, which currently has support for Portuguese, acting through support and empowering the patient to take care of their health. Understanding the logical implications and adaptations required for the understanding of texts in different languages can provide information for the application of the same procedures to other languages, correlating information and establishing logics for translations and treatment of specific terms of the area, allowing to supply a greater demand of patients who require continuous treatment. For the development of the project, it was used approaches and techniques aimed at scaling and language expansion in a dynamic way. For this in addition to the system-specific changes decisions tools like NLTK were used, aiming at the improvement and accomplishment of the necessary adaptations to the project, since this tool has support to several languages and is constantly improving. The results, analyzed using accuracy, precision and recall techniques, demonstrate that the improvement observed with the system adaptations to support the languages of interest were positive and significant, with an increase of 13% in recall and accuracy indicators and maintenance of 100% of precision. Thus, CleverCare performed well and was able to classify messages correctly, allowing the system to correctly recognize and classify different languages. This solution allows the system not only to process dialogues in Portuguese, English and Spanish, but also to enter the international market with the possibility of expansion and scalability for other languages

Lin Wai-yip. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2001. / Includes bibliographical references (leaves 114-123). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Information Extraction --- p.1 / Chapter 1.2 --- IE from Semi-structured Documents --- p.3 / Chapter 1.3 --- Thesis Contributions --- p.7 / Chapter 1.4 --- Thesis Organization --- p.9 / Chapter 2 --- Related Work --- p.11 / Chapter 2.1 --- Existing Approaches --- p.11 / Chapter 2.2 --- Limitations of Existing Approaches --- p.18 / Chapter 2.3 --- Our HISER Approach --- p.20 / Chapter 3 --- System Overview --- p.23 / Chapter 3.1 --- Hierarchical record Structure and Extraction Rule learning (HISER) --- p.23 / Chapter 3.2 --- Hierarchical Record Structure --- p.29 / Chapter 3.3 --- Extraction Rule --- p.29 / Chapter 3.4 --- Wrapper Adaptation --- p.32 / Chapter 4 --- Automatic Hierarchical Record Structure Construction --- p.34 / Chapter 4.1 --- Motivation --- p.34 / Chapter 4.2 --- Hierarchical Record Structure Representation --- p.36 / Chapter 4.3 --- Constructing Hierarchical Record Structure --- p.38 / Chapter 5 --- Extraction Rule Induction --- p.43 / Chapter 5.1 --- Rule Representation --- p.43 / Chapter 5.2 --- Extraction Rule Induction Algorithm --- p.47 / Chapter 6 --- Experimental Results of Wrapper Learning --- p.54 / Chapter 6.1 --- Experimental Methodology --- p.54 / Chapter 6.2 --- Results on Electronic Appliance Catalogs --- p.56 / Chapter 6.3 --- Results on Book Catalogs --- p.60 / Chapter 6.4 --- Results on Seminar Announcements --- p.62 / Chapter 7 --- Adapting Wrappers to Unseen Information Sources --- p.69 / Chapter 7.1 --- Motivation --- p.69 / Chapter 7.2 --- Support Vector Machines --- p.72 / Chapter 7.3 --- Feature Selection --- p.76 / Chapter 7.4 --- Automatic Annotation of Training Examples --- p.80 / Chapter 7.4.1 --- Building SVM Models --- p.81 / Chapter 7.4.2 --- Seeking Potential Training Example Candidates --- p.82 / Chapter 7.4.3 --- Classifying Potential Training Examples --- p.84 / Chapter 8 --- Experimental Results of Wrapper Adaptation --- p.86 / Chapter 8.1 --- Experimental Methodology --- p.86 / Chapter 8.2 --- Results on Electronic Appliance Catalogs --- p.89 / Chapter 8.3 --- Results on Book Catalogs --- p.93 / Chapter 9 --- Conclusions and Future Work --- p.97 / Chapter 9.1 --- Conclusions --- p.97 / Chapter 9.2 --- Future Work --- p.100 / Chapter A --- Sample Experimental Pages --- p.101 / Chapter B --- Detailed Experimental Results of Wrapper Adaptation of HISER --- p.109 / Bibliography --- p.114

Chan, Shuk Fong. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2002. / Includes bibliographical references (leaves 114-122). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Overview --- p.1 / Chapter 1.2 --- Thesis Contributions --- p.5 / Chapter 1.3 --- Thesis Outline --- p.9 / Chapter 2 --- Background --- p.10 / Chapter 2.1 --- Mixed-Initiative Interactions --- p.11 / Chapter 2.2 --- Mixed-Initiative Spoken Dialog Systems --- p.14 / Chapter 2.2.1 --- Finite-state Networks --- p.16 / Chapter 2.2.2 --- Form-based Approaches --- p.17 / Chapter 2.2.3 --- Sequential Decision Approaches --- p.18 / Chapter 2.2.4 --- Machine Learning Approaches --- p.20 / Chapter 2.3 --- Understanding Mixed-Initiative Dialogs --- p.24 / Chapter 2.4 --- Cooperative Response Generation --- p.26 / Chapter 2.4.1 --- Plan-based Approach --- p.27 / Chapter 2.4.2 --- Constraint-based Approach --- p.28 / Chapter 2.5 --- Chapter Summary --- p.29 / Chapter 3 --- Mixed-Initiative Dialog Management in the ISIS system --- p.30 / Chapter 3.1 --- The ISIS Domain --- p.31 / Chapter 3.1.1 --- System Overview --- p.31 / Chapter 3.1.2 --- Domain-Specific Constraints --- p.33 / Chapter 3.2 --- Discourse and Dialog --- p.34 / Chapter 3.2.1 --- Discourse Inheritance --- p.37 / Chapter 3.2.2 --- Mixed-Initiative Dialogs --- p.41 / Chapter 3.3 --- Challenges and New Directions --- p.45 / Chapter 3.3.1 --- A Learning System --- p.46 / Chapter 3.3.2 --- Combining Interaction and Delegation Subdialogs --- p.49 / Chapter 3.4 --- Chapter Summary --- p.57 / Chapter 4 --- Understanding Mixed-Initiative Human-Human Dialogs --- p.59 / Chapter 4.1 --- The CU Restaurants Domain --- p.60 / Chapter 4.2 --- "Task Goals, Dialog Acts, Categories and Annotation" --- p.61 / Chapter 4.2.1 --- Task Goals and Dialog Acts --- p.61 / Chapter 4.2.2 --- Semantic and Syntactic Categories --- p.64 / Chapter 4.2.3 --- Annotating the Training Sentences --- p.65 / Chapter 4.3 --- Selective Inheritance Strategy --- p.67 / Chapter 4.3.1 --- Category Inheritance Rules --- p.67 / Chapter 4.3.2 --- Category Refresh Rules --- p.73 / Chapter 4.4 --- Task Goal and Dialog Act Identification --- p.78 / Chapter 4.4.1 --- Belief Networks Development --- p.78 / Chapter 4.4.2 --- Varying the Input Dimensionality --- p.80 / Chapter 4.4.3 --- Evaluation --- p.80 / Chapter 4.5 --- Procedure for Discourse Inheritance --- p.83 / Chapter 4.6 --- Chapter Summary --- p.86 / Chapter 5 --- Cooperative Response Generation in Mixed-Initiative Dialog Modeling --- p.88 / Chapter 5.1 --- System Overview --- p.89 / Chapter 5.1.1 --- State Space Generation --- p.89 / Chapter 5.1.2 --- Task Goal and Dialog Act Generation for System Response --- p.92 / Chapter 5.1.3 --- Response Frame Generation --- p.93 / Chapter 5.1.4 --- Text Generation --- p.100 / Chapter 5.2 --- Experiments and Results --- p.100 / Chapter 5.2.1 --- Subjective Results --- p.103 / Chapter 5.2.2 --- Objective Results --- p.105 / Chapter 5.3 --- Chapter Summary --- p.105 / Chapter 6 --- Conclusions --- p.108 / Chapter 6.1 --- Summary --- p.108 / Chapter 6.2 --- Contributions --- p.110 / Chapter 6.3 --- Future Work --- p.111 / Bibliography --- p.113 / Chapter A --- Domain-Specific Task Goals in CU Restaurants Domain --- p.123 / Chapter B --- Full list of VERBMOBIL-2 Dialog Acts --- p.124 / Chapter C --- Dialog Acts for Customer Requests and Waiter Responses in CU Restaurants Domain --- p.125 / Chapter D --- The Two Grammers for Task Goal and Dialog Act Identifi- cation --- p.130 / Chapter E --- Category Inheritance Rules --- p.143 / Chapter F --- Category Refresh Rules --- p.149 / Chapter G --- Full list of Response Trigger Words --- p.154 / Chapter H --- Evaluation Test Questionnaire for Dialog System in CU Restaurants Domain --- p.159 / Chapter I --- Details of the statistical testing Regarding Grice's Maxims and User Satisfaction --- p.161

Wong, Chin Chung. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2002. / Includes bibliographical references (leaves 137-143). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Objectives --- p.3 / Chapter 1.2 --- Thesis Outline --- p.5 / Chapter 2 --- Background in Natural Language Understanding --- p.6 / Chapter 2.1 --- Rule-based Approaches --- p.7 / Chapter 2.2 --- Corpus-based Approaches --- p.8 / Chapter 2.2.1 --- Stochastic Approaches --- p.8 / Chapter 2.2.2 --- Phrase-spotting Approaches --- p.9 / Chapter 2.3 --- The ATIS Domain --- p.10 / Chapter 2.3.1 --- Chinese Corpus Preparation --- p.11 / Chapter 3 --- Semi-automatic Grammar Induction - Baseline Approach --- p.13 / Chapter 3.1 --- Background in Grammar Induction --- p.13 / Chapter 3.1.1 --- Simulated Annealing --- p.14 / Chapter 3.1.2 --- Bayesian Grammar Induction --- p.14 / Chapter 3.1.3 --- Probabilistic Grammar Acquisition --- p.15 / Chapter 3.2 --- Semi-automatic Grammar Induction 一 Baseline Approach --- p.16 / Chapter 3.2.1 --- Spatial Clustering --- p.16 / Chapter 3.2.2 --- Temporal Clustering --- p.18 / Chapter 3.2.3 --- Post-processing --- p.19 / Chapter 3.2.4 --- Four Aspects for Enhancements --- p.20 / Chapter 3.3 --- Chapter Summary --- p.22 / Chapter 4 --- Semi-automatic Grammar Induction - Enhanced Approach --- p.23 / Chapter 4.1 --- Evaluating Induced Grammars --- p.24 / Chapter 4.2 --- Stopping Criterion --- p.26 / Chapter 4.2.1 --- Cross-checking with Recall Values --- p.29 / Chapter 4.3 --- Improvements on Temporal Clustering --- p.32 / Chapter 4.3.1 --- Evaluation --- p.39 / Chapter 4.4 --- Improvements on Spatial Clustering --- p.46 / Chapter 4.4.1 --- Distance Measures --- p.48 / Chapter 4.4.2 --- Evaluation --- p.57 / Chapter 4.5 --- Enhancements based on Intelligent Selection --- p.62 / Chapter 4.5.1 --- Informed Selection between Spatial Clustering and Tem- poral Clustering --- p.62 / Chapter 4.5.2 --- Selecting the Number of Clusters Per Iteration --- p.64 / Chapter 4.5.3 --- An Example for Intelligent Selection --- p.64 / Chapter 4.5.4 --- Evaluation --- p.68 / Chapter 4.6 --- Chapter Summary --- p.71 / Chapter 5 --- Bidirectional Machine Translation using Induced Grammars ´ؤBaseline Approach --- p.73 / Chapter 5.1 --- Background in Machine Translation --- p.75 / Chapter 5.1.1 --- Rule-based Machine Translation --- p.75 / Chapter 5.1.2 --- Statistical Machine Translation --- p.76 / Chapter 5.1.3 --- Knowledge-based Machine Translation --- p.77 / Chapter 5.1.4 --- Example-based Machine Translation --- p.78 / Chapter 5.1.5 --- Evaluation --- p.79 / Chapter 5.2 --- Baseline Configuration on Bidirectional Machine Translation System --- p.84 / Chapter 5.2.1 --- Bilingual Dictionary --- p.84 / Chapter 5.2.2 --- Concept Alignments --- p.85 / Chapter 5.2.3 --- Translation Process --- p.89 / Chapter 5.2.4 --- Two Aspects for Enhancements --- p.90 / Chapter 5.3 --- Chapter Summary --- p.91 / Chapter 6 --- Bidirectional Machine Translation ´ؤ Enhanced Approach --- p.92 / Chapter 6.1 --- Concept Alignments --- p.93 / Chapter 6.1.1 --- Enhanced Alignment Scheme --- p.95 / Chapter 6.1.2 --- Experiment --- p.97 / Chapter 6.2 --- Grammar Checker --- p.100 / Chapter 6.2.1 --- Components for Grammar Checking --- p.101 / Chapter 6.3 --- Evaluation --- p.117 / Chapter 6.3.1 --- Bleu Score Performance --- p.118 / Chapter 6.3.2 --- Modified Bleu Score --- p.122 / Chapter 6.4 --- Chapter Summary --- p.130 / Chapter 7 --- Conclusions --- p.131 / Chapter 7.1 --- Summary --- p.131 / Chapter 7.2 --- Contributions --- p.134 / Chapter 7.3 --- Future work --- p.136 / Bibliography --- p.137 / Chapter A --- Original SQL Queries --- p.144 / Chapter B --- Seeded Categories --- p.146 / Chapter C --- 3 Alignment Categories --- p.147 / Chapter D --- Labels of Syntactic Structures in Grammar Checker --- p.148

Ho Chao Yang. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1998. / Includes bibliographical references (leaves 157-163). / Abstract also in Chinese. / Abstract --- p.i / Acknowledgment --- p.iii / List of Figures --- p.viii / List of Tables --- p.xiv / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Automatic Document Categorization --- p.1 / Chapter 1.2 --- Information Filtering --- p.3 / Chapter 1.3 --- Contributions --- p.6 / Chapter 1.4 --- Organization of the Thesis --- p.7 / Chapter 2 --- Related Work --- p.9 / Chapter 2.1 --- Existing Automatic Document Categorization Approaches --- p.9 / Chapter 2.1.1 --- Rule-Based Approach --- p.10 / Chapter 2.1.2 --- Similarity-Based Approach --- p.13 / Chapter 2.2 --- Existing Information Filtering Approaches --- p.19 / Chapter 2.2.1 --- Information Filtering Systems --- p.19 / Chapter 2.2.2 --- Filtering in TREC --- p.21 / Chapter 3 --- Document Pre-Processing --- p.23 / Chapter 3.1 --- Document Representation --- p.23 / Chapter 3.2 --- Classification Scheme Learning Strategy --- p.26 / Chapter 4 --- A New Approach - IBRI --- p.31 / Chapter 4.1 --- Overview of Our New IBRI Approach --- p.31 / Chapter 4.2 --- The IBRI Representation and Definitions --- p.34 / Chapter 4.3 --- The IBRI Learning Algorithm --- p.37 / Chapter 5 --- IBRI Experiments --- p.43 / Chapter 5.1 --- Experimental Setup --- p.43 / Chapter 5.2 --- Evaluation Metric --- p.45 / Chapter 5.3 --- Results --- p.46 / Chapter 6 --- A New Approach - GIS --- p.50 / Chapter 6.1 --- Motivation of GIS --- p.50 / Chapter 6.2 --- Similarity-Based Learning --- p.51 / Chapter 6.3 --- The Generalized Instance Set Algorithm (GIS) --- p.58 / Chapter 6.4 --- Using GIS Classifiers for Classification --- p.63 / Chapter 6.5 --- Time Complexity --- p.64 / Chapter 7 --- GIS Experiments --- p.68 / Chapter 7.1 --- Experimental Setup --- p.68 / Chapter 7.2 --- Results --- p.73 / Chapter 8 --- A New Information Filtering Approach Based on GIS --- p.87 / Chapter 8.1 --- Information Filtering Systems --- p.87 / Chapter 8.2 --- GIS-Based Information Filtering --- p.90 / Chapter 9 --- Experiments on GIS-based Information Filtering --- p.95 / Chapter 9.1 --- Experimental Setup --- p.95 / Chapter 9.2 --- Results --- p.100 / Chapter 10 --- Conclusions and Future Work --- p.108 / Chapter 10.1 --- Conclusions --- p.108 / Chapter 10.2 --- Future Work --- p.110 / Chapter A --- Sample Documents in the corpora --- p.111 / Chapter B --- Details of Experimental Results of GIS --- p.120 / Chapter C --- Computational Time of Reuters-21578 Experiments --- p.141

Wai Ip Lam. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1998. / Includes bibliographical references (leaves 84-87). / Text in English; abstract also in Chinese. / Wai Ip Lam. / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Background --- p.5 / Chapter 2.1 --- Information Retrieval --- p.5 / Chapter 2.1.1 --- Index Extraction --- p.6 / Chapter 2.1.2 --- Other Approaches to Extracting Indexes --- p.7 / Chapter 2.1.3 --- Conceptual Information Retrieval --- p.8 / Chapter 2.1.4 --- Information Extraction --- p.9 / Chapter 2.2 --- Natural Language Parsing --- p.9 / Chapter 2.2.1 --- Linguistics-based --- p.10 / Chapter 2.2.2 --- Corpus-based --- p.11 / Chapter 3 --- Concept Extraction --- p.13 / Chapter 3.1 --- Concepts in Sentences --- p.13 / Chapter 3.1.1 --- Semantic Structures and Themantic Roles --- p.13 / Chapter 3.1.2 --- Syntactic Functions --- p.14 / Chapter 3.2 --- Representing Concepts --- p.15 / Chapter 3.3 --- Application to Conceptual Information Retrieval --- p.18 / Chapter 3.4 --- Overview of Our Concept Extraction Model --- p.20 / Chapter 3.4.1 --- Corpus Training --- p.21 / Chapter 3.4.2 --- Sentence Analyzing --- p.22 / Chapter 4 --- Noun Phrase Detection --- p.23 / Chapter 4.1 --- Significance of Noun Phrase Detection --- p.23 / Chapter 4.1.1 --- Noun Phrases versus Terminals in Parse Trees --- p.23 / Chapter 4.1.2 --- Quantitative Analysis of Applying Noun Phrase Detection --- p.26 / Chapter 4.2 --- An Algorithm for Chinese Noun Phrase Partial Parsing --- p.28 / Chapter 4.2.1 --- The Hybrid Approach --- p.28 / Chapter 4.2.2 --- CNP3´ؤThe Chinese NP Partial Parser --- p.30 / Chapter 5 --- Rule Extraction and SVO Parsing --- p.35 / Chapter 5.1 --- Annotation of Corpora --- p.36 / Chapter 5.1.1 --- Components of Chinese Sentence Patterns --- p.36 / Chapter 5.1.2 --- Annotating Sentence Structures --- p.37 / Chapter 5.1.3 --- Illustrative Examples --- p.38 / Chapter 5.2 --- Parsing with Rules Obtained Directly from Corpora --- p.43 / Chapter 5.2.1 --- Extracting Rules --- p.43 / Chapter 5.2.2 --- Parsing --- p.44 / Chapter 5.3 --- Using Word Specific Information --- p.45 / Chapter 6 --- Generalization of Rules --- p.48 / Chapter 6.1 --- Essence of Chinese Linguistics on Generalization --- p.49 / Chapter 6.1.1 --- Classification of Chinese Sentence Patterns --- p.50 / Chapter 6.1.2 --- Revision of Chinese Verb Phrase Classification --- p.52 / Chapter 6.2 --- Initial Generalization --- p.53 / Chapter 6.2.1 --- Generalizing Rules --- p.55 / Chapter 6.2.2 --- Dealing with Alternative Results --- p.58 / Chapter 6.2.3 --- Parsing --- p.58 / Chapter 6.2.4 --- An illustrative Example --- p.59 / Chapter 6.3 --- Further Generalization --- p.60 / Chapter 7 --- Experiments on SVO Parsing --- p.62 / Chapter 7.1 --- Experimental Setup --- p.63 / Chapter 7.2 --- Effect of Adopting Noun Phrase Detection --- p.65 / Chapter 7.3 --- Results of Generalization --- p.68 / Chapter 7.4 --- Reliability Evaluation --- p.69 / Chapter 7.4.1 --- Covergence Sequence Tests --- p.69 / Chapter 7.4.2 --- Cross Evaluation Tests --- p.72 / Chapter 7.5 --- Overall Performance --- p.75 / Chapter 8 --- Conclusions --- p.79 / Chapter 8.1 --- Summary --- p.79 / Chapter 8.2 --- Contribution --- p.81 / Chapter 8.3 --- Future Directions --- p.81 / Chapter 8.3.1 --- Improvements in Parsing --- p.81 / Chapter 8.3.2 --- Concept Representations --- p.82 / Chapter 8.3.3 --- Non-IR Applications --- p.83 / Bibliography --- p.84 / Appendix --- p.88 / Chapter A --- The Extended Part of Speech Tag Set --- p.88

This thesis presents novel tasks and deep learning methods for machine reading comprehension and question answering with the goal of achieving natural language understanding. First, we consider a semantic parsing task where the model understands sentences and translates them into a logical form or instructions. We present a novel semi-supervised sequential autoencoder that considers language as a discrete sequential latent variable and semantic parses as the observations. This model allows us to leverage synthetically generated unpaired logical forms, and thereby alleviate the lack of supervised training data. We show the semi-supervised model outperforms a supervised model when trained with the additional generated data. Second, reading comprehension requires integrating information and reasoning about events, entities, and their relations across a full document. Question answering is conventionally used to assess reading comprehension ability, in both artificial agents and children learning to read. We propose a new, challenging, supervised reading comprehension task. We gather a large-scale dataset of news stories from the CNN and Daily Mail websites with Cloze-style questions created from the highlights. This dataset allows for the first time training deep learning models for reading comprehension. We also introduce novel attention-based models for this task and present qualitative analysis of the attention mechanism. Finally, following the recent advances in reading comprehension in both models and task design, we further propose a new task for understanding complex narratives, NarrativeQA, consisting of full texts of books and movie scripts. We collect human written questions and answers based on high-level plot summaries. This task is designed to encourage development of models for language understanding; it is designed so that successfully answering their questions requires understanding the underlying narrative rather than relying on shallow pattern matching or salience. We show that although humans solve the tasks easily, standard reading comprehension models struggle on the tasks presented here.

Medical Information Visualization makes optimized use of digitized data of medical records, e.g. Electronic Medical Record. This thesis is an extended work of Pictorial Information Visualization System (PIVS) developed by Yongji Jin (Jin, 2016) Jiaren Suo (Suo, 2017) which is a graphical visualization system by picturizing patient’s medical history summary depicting patients’ medical information in order to help patients and doctors to easily capture patients’ past and present conditions. The summary information has been manually entered into the interface where the information can be taken from clinical notes. This study proposes a methodology of automatically extracting medical information from patients’ clinical notes by using the techniques of Natural Language Processing in order to produce medical history summarization from past medical records. We develop a Named Entities Recognition system to extract the information of the medical imaging procedure (performance date, human body location, imaging results and so on) and medications (medication names, frequency and quantities) by applying the model of conditional random fields with three main features and others: word-based, part-of-speech, Metamap semantic features. Adding Metamap semantic features is a novel idea which raised the accuracy compared to previous studies. Our evaluation shows that our model has higher accuracy than others on medication extraction as a case study. For enhancing the accuracy of entities extraction, we also propose a methodology of Topic Segmentation to clinical notes using boundary detection by determining the difference of classification probabilities of subsequence sequences, which is different from the traditional Topic Segmentation approaches such as TextTiling, TopicTiling and Beeferman Statistical Model. With Topic Segmentation combined for Named Entities Extraction, we observed higher accuracy for medication extraction compared to the case without the segmentation. Finally, we also present a prototype of integrating our information extraction system with PIVS by simply building the database of interface coordinates and the terms of human body parts.

This thesis describes the research efforts on pivot-based statistical machine translation (SMT) for morphologically rich languages (MRL). We provide a framework to translate to and from morphologically rich languages especially in the context of having little or no parallel corpora between the source and the target languages. We basically address three main challenges. The first one is the sparsity of data as a result of morphological richness. The second one is maximizing the precision and recall of the pivoting process itself. And the last one is making use of any parallel data between the source and the target languages. To address the challenge of data sparsity, we explored a space of tokenization schemes and normalization options. We also examined a set of six detokenization techniques to evaluate detokenized and orthographically corrected (enriched) output. We provide a recipe of the best settings to translate to one of the most challenging languages, namely Arabic. Our best model improves the translation quality over the baseline by 1.3 BLEU points. We also investigated the idea of separation between translation and morphology generation. We compared three methods of modeling morphological features. Features can be modeled as part of the core translation. Alternatively these features can be generated using target monolingual context. Finally, the features can be predicted using both source and target information. In our experimental results, we outperform the vanilla factored translation model. In order to decide on which features to translate, generate or predict, a detailed error analysis should be provided on the system output. As a result, we present AMEANA, an open-source tool for error analysis of natural language processing tasks, targeting morphologically rich languages. The second challenge we are concerned with is the pivoting process itself. We discuss several techniques to improve the precision and recall of the pivot matching. One technique to improve the recall works on the level of the word alignment as an optimization process for pivoting driven by generating phrase pairs between source and target languages. Despite the fact that improving the recall of the pivot matching improves the overall translation quality, we also need to increase the precision of the pivot quality. To achieve this, we introduce quality constraints scores to determine the quality of the pivot phrase pairs between source and target languages. We show positive results for different language pairs which shows the consistency of our approaches. In one of our best models we reach an improvement of 1.2 BLEU points. The third challenge we are concerned with is how to make use of any parallel data between the source and the target languages. We build on the approach of improving the precision of the pivoting process and the methods of combination between the pivot system and the direct system built from the parallel data. In one of the approaches, we introduce morphology constraint scores which are added to the log linear space of features in order to determine the quality of the pivot phrase pairs. We compare two methods of generating the morphology constraints. One method is based on hand-crafted rules relying on our knowledge of the source and target languages; while in the other method, the morphology constraints are induced from available parallel data between the source and target languages which we also use to build a direct translation model. We then combine both the pivot and direct models to achieve better coverage and overall translation quality. Using induced morphology constraints outperformed the handcrafted rules and improved over our best model from all previous approaches by 0.6 BLEU points (7.2/6.7 BLEU points from the direct and pivot baselines respectively). Finally, we introduce applying smart techniques to combine pivot and direct models. We show that smart selective combination can lead to a large reduction of the pivot model without affecting the performance and in some cases improving it.