English-Korean Machine Translation System

Slides:



Advertisements
Similar presentations
School of something FACULTY OF OTHER School of Computing FACULTY OF ENGINEERING Chunking: Shallow Parsing Eric Atwell, Language Research Group.
Advertisements

Machine Translation. Can you imagine working as a translator without the help of computer?
Natural Language Processing Projects Heshaam Feili
A Syntactic Translation Memory Vincent Vandeghinste Centre for Computational Linguistics K.U.Leuven
Chapter Chapter Summary Languages and Grammars Finite-State Machines with Output Finite-State Machines with No Output Language Recognition Turing.
LING NLP 1 Introduction to Computational Linguistics Martha Palmer April 19, 2006.
Machine Translation Prof. Alexandros Potamianos Dept. of Electrical & Computer Engineering Technical University of Crete, Greece May 2003.
Natural Language Query Interface Mostafa Karkache & Bryce Wenninger.
1 Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang, Assistant Professor Dept. of Computer Science & Information Engineering National Central.
Semi-Automatic Learning of Transfer Rules for Machine Translation of Low-Density Languages Katharina Probst April 5, 2002.
Language Center Online System Feature Upgrade and Application Jenny Jen Language Center National Central University.
Creation of a Russian-English Translation Program Karen Shiells.
1 A Chart Parser for Analyzing Modern Standard Arabic Sentence Eman Othman Computer Science Dept., Institute of Statistical Studies and Research (ISSR),
CS-EE 481 Spring Founders Day, 2005 University of Portland School of Engineering Project Pocket Gopher Conversational Learning Agent Team Josh Jones.
Machine Translation Dr. Radhika Mamidi. What is Machine Translation? A sub-field of computational linguistics It investigates the use of computer software.
ICS611 Introduction to Compilers Set 1. What is a Compiler? A compiler is software (a program) that translates a high-level programming language to machine.
Chapter 1 Introduction Dr. Frank Lee. 1.1 Why Study Compiler? To write more efficient code in a high-level language To provide solid foundation in parsing.
Experiments on Building Language Resources for Multi-Modal Dialogue Systems Goals identification of a methodology for adapting linguistic resources for.
ESLG 320 Ch. 12 A little grammar language…. Parts of Speech  Noun: a person/place/thing/idea  Verb: an action or a state of being  Adjective: a word.
Overview Project Goals –Represent a sentence in a parse tree –Use parses in tree to search another tree containing ontology of project management deliverables.
Machine Translation  Machine translation is of one of the earliest uses of AI  Two approaches:  Traditional approach using grammars, rewrite rules,
11 Chapter 14 Part 1 Statistical Parsing Based on slides by Ray Mooney.
The Parts of Speech By Ms. Walsh The 8 Parts of Speech… Nouns Adjectives Pronouns Verbs Adverbs Conjunctions Prepositions Interjections Walsh Publishing.
Interdisciplinary Workshop, Kobe University, October 30, 2008 Designing an Interactive System for the Grammatical Analysis of Written Romanian Objectives,
What you have learned and how you can use it : Grammars and Lexicons Parts I-III.
The Parts of Speech The 8 Parts of Speech… Nouns Adjectives Pronouns Verbs Adverbs Conjunctions Prepositions Interjections.
Grammars Grammars can get quite complex, but are essential. Syntax: the form of the text that is valid Semantics: the meaning of the form – Sometimes semantics.
LANGUAGE ARTS LA WORKS UNIT 3 REVIEW STUDY GUIDE.
For Friday Finish chapter 23 Homework –Chapter 23, exercise 15.
CPSC 422, Lecture 27Slide 1 Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 27 Nov, 16, 2015.
Natural Language Processing Slides adapted from Pedro Domingos
AUTONOMOUS REQUIREMENTS SPECIFICATION PROCESSING USING NATURAL LANGUAGE PROCESSING - Vivek Punjabi.
Sentence Structure By: Amanda Garrett Bailey. What is the function of: Nouns Pronouns Verbs Adjectives Adverbs.
Overview of Statistical NLP IR Group Meeting March 7, 2006.
NATURAL LANGUAGE PROCESSING
23.3 Information Extraction More complicated than an IR (Information Retrieval) system. Requires a limited notion of syntax and semantics.
A Simple English-to-Punjabi Translation System By : Shailendra Singh.
Pre-processing Tasks for Rule- Based English-Korean Machine Translation System Sung-Dong Kim, Dept. of Computer Engineering, Hansung University, Seoul,
CHAPTER 1 INTRODUCTION TO COMPILER SUNG-DONG KIM, DEPT. OF COMPUTER ENGINEERING, HANSUNG UNIVERSITY.
Approaches to Machine Translation
CS 326 Programming Languages, Concepts and Implementation
Lecture – VIII Monojit Choudhury RS, CSE, IIT Kharagpur
Words, Phrases, Clauses, & Sentences
Statistical NLP: Lecture 3
My Digital Vocabulary Notebook
A Parser for Sinhala Language First Step Towards English to Sinhala Machine Translation
Google translate app demo
Dept of Computer Science
How Do We Translate? Methods of Translation The Process of Translation.
Modular HPSG Vlado Keselj presented by Lijun Hou
Syntactic Category Prediction for Improving Translation Quality in English-Korean Machine Translation Sung-Dong Kim, Dept. of Computer Engineering, Hansung.
Nouns Nouns not noun noun noun not not
Translation Problems.
Machine Learning in Natural Language Processing
Writing Analytics Clayton Clemens Vive Kumar.
Tagging and Statistically Translating Latin Sentences
Development of an Online Adaptive Vocabulary Test System
CSE322 LEFT & RIGHT LINEAR REGULAR GRAMMAR
Automated MS Word and PowerPoint Translator
My Digital Vocabulary Notebook
Natural Language - General
Approaches to Machine Translation
Introduction to Machine Translation
Linguistic Essentials
CS246: Information Retrieval
Week 9 Warm-Ups English 12 Mrs. Fountain.
PRESENTATION: GROUP # 5 Roll No: 14,17,25,36,37 TOPIC: STATISTICAL PARSING AND HIDDEN MARKOV MODEL.
Parts of Speech II.
Artificial Intelligence 2004 Speech & Natural Language Processing
Using Dictionaries in Translation (223 TRAJ)
Presentation transcript:

English-Korean Machine Translation System Sung-Dong Kim Dept. of Computer System Engineering, Hansung University

Dept. of CSE, Hansung Univ. Contents History Methodologies System Structure Capabilities of EKMT System Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. History (1) KSHALT (Korean System for Human Assisted Language Translation) Late 1980’s Implemented using LISP Run on IBM 3090 mainframe Enkor 1991 ~ 1995 Implemented using C Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. History (2) ETran Several versions: 98, 99, 2000, 2003 Enhanced version of Enkor Text translation, internet translation on browser SmarTran 2004 Provide more user-friendly capabilities Improve dictionary access time Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Methodologies (1) Rule-based method Transfer method Idiom-based analysis and translation Statistical method Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Methodologies (2) Rule-based method Context free grammar Phrase, clause, sentence structures Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Methodologies (3) Transfer method Using transfer rules About 70 rules Structural transfer for catching up with the differences between English and Korean “little”: negative meaning in Korean It ~ to-INF: real, pseudo subject, object relation … Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Methodologies (4) Idiom-based analysis and translation Reduce analysis complexity Enhance translation quality bread and butter: Not bread and butter but bread spread with butter Takes one edge instead of three in chart provide him with money Provide A with B Give him a money Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Methodologies (5) Statistical method: intra-sentence segmentation based on maximum entropy Partial parsing: reduce parsing complexity  long sentence analysis Maximum entropy probability model Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Structure (1) English sentences Lexical Rules Lexical Analysis Lexical Dictionary Syntactic Rules Syntactic Analysis EK Transfer Dictionary Transfer EK Transfer Rules Korean Dictionary Korean Generation Korean Generation Rules Korean sentences Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Structure (2) System modules Lexical analysis Syntactic analysis: Parser Chart-based parsing Idiom-based analysis Idiom recognition before parsing Partial parsing using intra-sentence segmentation Transfer Korean generation Dept. of CSE, Hansung Univ.

Result of lexical analysis Intra-sentence segmentation Segment 1 Segment 2 … Segment n EK Idiom Dictionary Idiom recognition & translation Grammar Segment Analysis Global structuring Tree selection Parser Parsing tree Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Structure (4) Dictionaries Lexical dictionaries Word usage dictionary About 70,000 entries Information for POS probability calculation Word information dictionary About 83,000 entries Information about POS, … Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Structure (5) EK transfer dictionary Structure Default meaning Collocations Idioms General dictionary For each POS: noun, adjective, adverb, verb, … Domain dictionary 14 types: military, economy, politics, computer, medical, … User dictionary Facility for user to make his own dictionary Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Structure (6) Statistics of transfer dictionary Number of entries General dictionary: about 68,000 Noun: 40,546 Adjective: 16,255 Adverb: 2,671 Verb: 8,612 Domain dictionary: about 36,000 Number of idioms: 42,600 Number of collocations: 6,150 Dept. of CSE, Hansung Univ.

Dept. of CSE, Hansung Univ. Structure (7) Rules Lexical rules Syntactic rules About 600 syntactic rules Transfer rules Korean generation rules Dept. of CSE, Hansung Univ.

Capabilities of EKMT system Text translation Internet translation on the browser MS-office document translation Dept. of CSE, Hansung Univ.