MIT Natural Language Processing first Lecture: Introduction and Overview (Part III) _mit

Natural language Processing: Background and overview
Natural Language Processing:background and Overview
Author: Regina Barzilay (Mit,eecs Department,september 8, 2004)
Translator: I love natural language processing (www.52nlp.cn, January 5, 2009)

What would this course contain (What will this course being about)?
1. Establish appropriate computational models and effective expressions for linguistic knowledge at different levels (syntactic, semantic, textual) (computationally suitable and expressive representation of linguistic Knowledge at various levels:syntax, semantics, discourse)
2, from the text sample learning about language characteristics of the algorithm: smoothing estimation, logarithmic linear model, probabilistic context-free grammar, EM algorithm, joint training, ... (Algorithms for learning language properties from Text samples:smoothed estimation, log-linear models, probabilistic cont Ext free grammars, the EM algorithm, co-training, ...)
3, the text processing technology based applications: Machine translation, text summary, information retrieval (technologies underlying text processing Applications:machine translation, text summarization, Information retrieval)

V. Syllabus (SYLLABUS)
Introduction and Overview (Introduction and Overview)--1 Class (1 Class)
Simple language statistics (Language Statistics)--1 Class (1 Class)
Language model (Language Models)--1 Class (1 Class)
Callout (Tagging)--1 Class (1 Class)
Syntactic analysis (syntactic parsing)--1 class (1 Class)
Unsupervised grammar induction (unsupervised grammar induction)--1 Lesson (1 Class)
Introduction to Lexical semantics (Introduction to lexical semantics)--1 Class (1 Class)
Meaning disambiguation (Word Sense disambiguation)--1 Class (1 Class)
Semantic analysis (semantic parsing)--1 class (1 Class)
Introduction to Discourse processing (Discourse processing)--1 Class (1 Class)
Anaphora digestion (anaphora resolution)--1 Class (1 Class)
Subject Division (topical segmentation)--1 Class (1 Class)
Discourse analysis (Discourse parsing)--1 Class (1 Class)
Dialog processing (dialogue processing)--1 Class (1 Class)
Natural language generation (Natural Language Generation)--1 Class (1 Class)
Text Summary (summarization)--1 Class (1 Class)
Information retrieval (Information Retrieval)--1 Class (1 Class)
Machine translation (Machine translation)--3 class (3 classes)

Vi. Preparatory Knowledge (prerequisites)
1, interested in language and understand the basic knowledge of English (interest in language and basic knowledge of 中文版)
2, understand some basic linear algebra, probability statistics knowledge (Some basic linear algebra, probability and statistics)
3, have BASIC programming foundation (Some programming skills)

Vii. Evaluation (Assessment)
1, midterm (midterm)--35%
2, two homework (two homeworks)--Each 15%
3. A submit project (project)--35%

Viii. Summary (Summary)
1. Statistical method vs. "Handmade" system (statistical approaches vs. hand-crafted systems)
A many rules need to be coded into human knowledge (Many rules are required to encode human knowledge)
b It is difficult to model the interaction between rules (Hard to model rule interaction)
(c) Common limitations of comparative elasticity (frequently constraints are soft)
2. Machine learning about NLP (Machine Learning for NLP)
(a) We need to compute the expression of language information more effectively (we need computationally effective representation of linguistic information)
b We need learning algorithms that are more appropriate for processing language data (we need new learning algorithms suitable for processing data)

Next talk (Next lecture): Word count (word counting)

The first lecture is over.
The second lecture: the word Count

Attached: Course and courseware pdf download mit English page address:
http://people.csail.mit.edu/regina/6881/

Note: This article according to the MIT Open Curriculum Creation sharing specification translation release, reprint please specify the source "I love Natural Language processing": www.52nlp.cn

from:http://www.52nlp.cn/mit-nlp-first-lesson-introduction-and-overview-third-part/