Introduction to NLP

Transcript

1. လ"စက%&န%&လည)တ+,စက)-uပ)eလ& eတ1အe3က%င)& eအ&56င)&ခiuင)
2. လ"စက%&န%&လည)တ+,စက)-uပ)eလ& eတ1အe3က%င)&e9ပ%ရeအ%င) Google Assistant Siri GOOGLE ဘ%စ<&ရလ+ VoiceTra (UCSY NLP Lab + NICT Research Center)
3. လ"န+=စက)-uပ)ရ+>က1%9ခ%&ခ?က) လ"eတ%ကiuစက*+e,ပ*တတ.eအ*င.သင.ရ တ*န45စက.6uပ.eတ%ကiuလ"စက*+န*+လည. eအ*င.သင.ရတ*တ"တ"ပ4လ*+?
4. ဘ%သ%စက%&တခuကiuန%&လည) တယ)လiuဘ%eတ1န+=ဆuD&9ဖတ)လ+ စ%ဖတ)တတ)တယ) စ%eရ&တတ)တယ) န%&eထ%င)တတ)တယ) 9ပန)e9ပ%တတ)တယ)
5. က1န)ပ?Gတ%eတ1ကiuလ"စက%&န%&လည) eအ%င)ဘယ)လiuသင)3ကမလ+?
6. Natural Language Processing Natural language processing (NLP) is a field of computer science, artificial intelligence, and computational linguistics concerned with the interactions between computers and human (natural) languages.
7. Real World NLP Search Engines Question And Answering (Chat Bots) Spam mail detection News recommendation Facebook Newsfeed Text Analytics
8. How does NLP Work? Morphology - What is a word? 
 I go to school - ကIန)eတ%)ဒ<eန=eက?%င)&သiuသ1%&သည)။ Lexicography - What does each word mean?
 He plays bass guitar. That bass was delicious! Syntax - How do the word relate to each other?
 The dog bit the man. ≠ The man bit the dog.
9. Semantics - How can we infer meaning from the sentence?
 The ipod is so small! 
 The monitor is so small! POS Tagging - Part of Speech Tagging
 Assigning an appropriate part of speech to a word
 ရန)ကuန) - Noun
 ကIန)eတ%) - Pronoun
 စ%& - Verb
 လ6ပ - Adjective Discourse - How about across many sentences?
 President Bush met with President-Elect Obama today at the White House. He welcomed him, and showed him around. Who is “he”? Who is “him”? How would a computer figure that out?
10. Application Areas Text Classification (Spam, sentiment analysis, opinion mining) Information Retrieval, Information Extraction (Topic Modeling, Text Summarization) Text To Speech (MyTTS developed by Myanmar Text To Speech Team) Speech to Text Recommender Systems
11. Machine Learning စက)eတ1ကiuလ"လiueတ1&5iuင)eအ%င)က"ည<eပ&တယ)
 Machine learning is a method of data analysis that automates analytical model building. Using algorithms that iteratively learn from data, machine learning allows computers to find hidden insights without being explicitly programmed where to look.
12. Machine Learning Techniques Association Analysis@Market Basket Analysis Supervised Learning Unsupervised Learning Reinforcement Learning Neural Network (Deep Learning)
13. Machine Learning Algorithms Linear Regression Logistic Regression Decision Trees SVM Naive Bayes KNN K-Means Random Forest
14. Implementation Python
 NLTK (Natural Language Processing Toolkit)
 Scikit-Learn (Machine Learning)
 Gensim (Topic Modeling)
 NumPy
 TextBlob
 Pandas (Data Visualization)
 Tensor Flow Machine Learning Framework JAVA
 Stanford Core NLP
 Weka
 Deeplearning4j
 MALLET (NLP)