Multilingual and Crosslingual Information System

 

         Room: 4260, Monday 9:10 - 12:00AM

         Instructor: Prof. Wen-Hsiang Lu

-          Office: 4288-1

-          Office hours: Monday 1:10 - 2:10PM

-          Phone: 62545

-          Web page: http://myweb.ncku.edu.tw/~whlu/mis.htm

-          Email: whlu@mail.ncku.edu.tw

-          Teaching assistant:

         王廷軒 (Email: playif@gmail.com)

         Source Textbooks

-          Christopher D. Manning and Hinrich Schutze. Foundations of Statistical Natural Language Processing. The MIT Press. 1999. (全華科技圖書 : 02-23717725)

-          Daniel Jurafsky and James H. Martin. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice Hall. 2000.

-          James Allen. Natural Language Understanding. Benjamin/Cummings Publishing Co. 1995.

-          Gregory Grefenstette. Cross-Language Information Retrieval. Kluwer. 1998.

-          Jean Veronis. Parallel Text Processing: Alignment and Use of Translation Corpora. Kluwer. 2000.

         Grading

-          Class participation/presentation:    30%

-          Tests:                                        25%

-          Project:                                          25%

-          Homeworks:                                          20%

         Topics

-          Lecture1: Introduction

-          Lecture2: Mathematical Foundations

-          Lecture3: Linguistics Essentials

-          Lecture4: Corpus-based Work

-          Lecture5: Collocations

-          Lecture6: Statistical Inference: n-gram Models over Sparse Data

-          Lecture7: Word Sense Disambiguation

-          Lecture8: Statistical Alignment and Machine Translation
(MT Reference provider: NCKU PhD candidate,
張耀升)

-          Lecture9: Markov Models (Reference provider: NCKU PhD, 夏啟峻)

-          Lecture10: Term Translation Extraction & Cross-Language Information Retrieval

-          Lecture11 : Statistical/Probabilistic Models for Word Alignment & CLIR

-          Lecture12: Part-of-Speech Tagging

-          Lecture13: Probabilistic Context Free Grammars

-          Lecture14: Question Answering

         Homework

-          Chinese-English sentence alignment (deadline: December 1, 2004)

         [Chinese-English dictionary]

         [Training data]

         Relevant Reading

-          Term Translation Extraction and CLIR

-          Chien-Cheng Wu & Jason S. Chang, Bilingual Collocation Extraction Based on Syntactic and Statistical Analyses, ROCLING XV, 2003

-          林語、高照明, 結合統計與語言訊息的混合式中英雙語句對應演算法, ROCLING XVI, 2004

-          Learn Question Focus and Dependency Relations from Web Search Results for Question Classification, modified from Master Thesis Oral Defense of林舒容, 2006