統計的言語モデル特論_E
|
|
Instructor(s) |
Mikio Yamamoto
|
myamaAtcsDottsukubaDotacDotjp | |
URL | http://www.coins.tsukuba.ac.jp/~myama/lecture/ |
Office hours | SB908, 11:00-12:00, Monday |
Cource# | 01CH603 |
Area | Intelligent Systems |
Basic/Advanced | |
Course style | lecture (in Japanese) |
Term | Fall A,B |
Period | Tue5,6 |
Room# | 総合B112-1 |
Keywords | Language models, Ngram models, Smoothing, Backoff-smoothing, Interpolation. |
Prerequisites | Elemental level of probability, statistics and information theory. Programming skill is needed for a final project. |
relation degree program competence | Knowledge Utilization Skills,Management Skills,Communication Skills,Research Skills,Expert Knowledge |
Goal | |
Outline | This course will introduce students to several modern techniques for generative models of natural human language such as Japanese. In particular, we will focus on methods for estimating probabilistic models of languages. |
Course plan |
1.Introduction 2.Probability theory and natural language 3.statistics 4.Introduction of ngram models and information theory 5.back-off smoothing methods 6.Interpolation and EM-algorithm 7.Maximum entropy models 8.Implementation of ngram language models 9.Design of probablistic models 10.Discussion for the final project |
Textbook | pdf files on the web. |
References |
(1)Kenji Kita, "Kakurituteki-gengo-moderu", 1999, (in Japanese). (2) |
Evaluation | Determining grades with final project performance and report. |
TF / TA | |
Misc. |
Open in an odd number year. 2015年度まで開講された「自然言語処理特論」(01CH603, 01CJ223)の単位を修得した者の履修は認めない。 |