Automatic topic detection of multi-lingual news stories.

• Other Authors: Wong, Kam Lai.
• Format: Others
• Language: English; Chinese
• Published: 2000
• Subjects: Broadcast journalism > Data processing; Information retrieval; English language > Data processing; Chinese language > Data processing
• Online Access: http://library.cuhk.edu.hk/record=b5890341; http://repository.lib.cuhk.edu.hk/en/item/cuhk-323212

Wong Kam Lai. === Thesis (M.Phil.)--Chinese University of Hong Kong, 2000. === Includes bibliographical references (leaves 92-98). === Abstracts in English and Chinese. === Chapter 1 --- Introduction --- p.1 === Chapter 1.1 --- Our Contributions --- p.5 === Chapter 1.2 --- Organization of this Thesis --- p.5 === Chapter 2 --- Literature Review --- p.7 === Chapter 2.1 --- Dragon Systems --- p.7 === Chapter 2.2 --- Carnegie Mellon University (CMU) --- p.9 === Chapter 2.3 --- University of Massachusetts (UMass) --- p.10 === Chapter 2.4 --- IBM T.J. Watson Research Center --- p.11 === Chapter 2.5 --- BBN Technologies --- p.12 === Chapter 2.6 --- National Taiwan University (NTU) --- p.13 === Chapter 2.7 --- Drawbacks of Existing Approaches --- p.14 === Chapter 3 --- Overview of Proposed Approach --- p.15 === Chapter 3.1 --- News Source --- p.15 === Chapter 3.2 --- Story Preprocessing --- p.18 === Chapter 3.3 --- Concept Term Generation --- p.20 === Chapter 3.4 --- Named Entity Extraction --- p.21 === Chapter 3.5 --- Gross Translation of Chinese to English --- p.21 === Chapter 3.6 --- Topic Detection method --- p.22 === Chapter 3.6.1 --- Deferral Period --- p.22 === Chapter 3.6.2 --- Detection Approach --- p.23 === Chapter 4 --- Concept Term Model --- p.25 === Chapter 4.1 --- Background of Contextual Analysis --- p.25 === Chapter 4.2 --- Concept Term Generation --- p.28 === Chapter 4.2.1 --- Concept Generation Algorithm --- p.28 === Chapter 4.2.2 --- Concept Term Representation for Detection --- p.33 === Chapter 5 --- Topic Detection Model --- p.35 === Chapter 5.1 --- Text Representation and Term Weights --- p.35 === Chapter 5.1.1 --- Story Representation --- p.35 === Chapter 5.1.2 --- Topic Representation --- p.43 === Chapter 5.1.3 --- Similarity Score --- p.43 === Chapter 5.1.4 --- Time adjustment scheme --- p.46 === Chapter 5.2 --- Gross Translation Method --- p.48 === Chapter 5.3 --- The Detection System --- p.50 === Chapter 5.3.1 --- Detection Requirement --- p.50 === Chapter 5.3.2 --- The Top Level Model --- p.52 === Chapter 5.4 --- The Clustering Algorithm --- p.55 === Chapter 5.4.1 --- Similarity Calculation --- p.55 === Chapter 5.4.2 --- Grouping Related Elements --- p.56 === Chapter 5.4.3 --- Topic Identification --- p.60 === Chapter 6 --- Experimental Results and Analysis --- p.63 === Chapter 6.1 --- Evaluation Model --- p.63 === Chapter 6.1.1 --- Evaluation Methodology --- p.64 === Chapter 6.2 --- Experiments on the effects of tuning the parameter --- p.68 === Chapter 6.2.1 --- Experiment Setup --- p.68 === Chapter 6.2.2 --- Results and Analysis --- p.69 === Chapter 6.3 --- Experiments on the effects of named entities and concept terms --- p.74 === Chapter 6.3.1 --- Experiment Setup --- p.74 === Chapter 6.3.2 --- Results and Analysis --- p.75 === Chapter 6.4 --- Experiments on the effect of using time adjustment --- p.77 === Chapter 6.4.1 --- Experiment Setup --- p.77 === Chapter 6.4.2 --- Results and Analysis --- p.79 === Chapter 6.5 --- Experiments on mono-lingual detection --- p.80 === Chapter 6.5.1 --- Experiment Setup --- p.80 === Chapter 6.5.2 --- Results and Analysis --- p.80 === Chapter 7 --- Conclusions and Future Work --- p.83 === Chapter 7.1 --- Conclusions --- p.83 === Chapter 7.2 --- Future Work --- p.85 === Chapter A --- List of Topics annotated for TDT3 Corpus --- p.86 === Chapter B --- Matching evaluation topics to hypothesized topics --- p.90 === Bibliography --- p.92