Govt. Eng. College painav 04-06-2010 Natural Language Processing Jaganadh G Process expert (NLP, ir & ie) r&d Division 365media inc. Coimbatore, India California , usa [email protected] www.365media.com
Jan 26, 2015
Govt. Eng. Collegepainav
04-06-2010
Natural Language Processing
Jaganadh GProcess expert (NLP, ir & ie)
r&d Division365media inc.
Coimbatore, IndiaCalifornia , usaJaganadhg@365media. in
www.365media.com
Govt. Eng. Collegepainav
04-06-2010
outline
➢Introduction➢History➢Areas in NLP➢Future of NLP➢References
Govt. Eng. Collegepainav
04-06-2010
Question ?
➢Have you ever used any NLP products/ NLP Powered tools ? ➢
➢
➢
Govt. Eng. Collegepainav
04-06-2010
Natural Language Processing
➢A sub-field of Artificial Intelligence (AI)➢An inter disciplinary subject ➢Aim:➢To build intelligent computers that can interact with human being like a human being !!
Govt. Eng. Collegepainav
04-06-2010
Natural Language ?
➢Natural Language?➢Refers to the language spoken by people, e.g. English, Japanese, Swahili, as opposed to artificial languages, like C++, Java, etc.
Govt. Eng. Collegepainav
04-06-2010
Definition
Natural Language Processing is a theoretically motivated range of computational techniques for analyzing and representing naturally occurring texts/speech at one or more levels of linguistic analysis for the purpose of achieving human-like language processing for a range of tasks or applications.
Govt. Eng. Collegepainav
04-06-2010
History
●Second World War !!!●Started with Machine Translation Research● Now:●The most promising technology solutions ●Labs --> Industry --> Layman
Govt. Eng. Collegepainav
04-06-2010
Why NLP
➢Huge amounts of data Internet = at least 20 billions pages
Text data web sites, blog, tweets .......–Audio data speech .......–
➢Applications for processing large amounts of texts require NLP expertise
Govt. Eng. Collegepainav
04-06-2010
Why nlp?
News:AN EARTHQUAKE struck Indonesia today - a strapping 7.7 magnitude earthquake that struck early today off the northern coast of the island of Sumatra. It caused minor damage and there are no reports of any deaths, although electricity was interrupted in several places.
Location : IndonesiaMagnitude: 7.7Region: Sumatra (Northern Cost)Deaths: NilDamage: Minor
Tweet@nokia announces release of new PDA phones see is.gd/iuTuY Who: NokiaWhat: Product announcement
Govt. Eng. Collegepainav
04-06-2010
Is NLP really hard to achieve
Govt. Eng. Collegepainav
04-06-2010
MAJOR Areas of Research & Development
➢Text Processing➢Morph Analyzer➢POS Tagging➢Parsing ➢Machine Translation .........➢Speech Processing ➢Text to Speech (TTS)➢Automatic Speech Recognition (ASR)➢Speech to Speech Translation
Govt. Eng. Collegepainav
04-06-2010
Text processing●Processing raw text
● Morphological Analysis● Running --> run + ing
● POS Tagging ● Ram/NNP goes/VB to/TO school/NNP ..
● Stemming● running --> run
● Parsing ● Identifying sentence structure ● S --> NP + VP .
Govt. Eng. Collegepainav
04-06-2010
Text processing
Machine Translation Translating content in one natural language to another natural languageExample : Translating and English Sentence to Malaylam with the help of a software.
Govt. Eng. Collegepainav
04-06-2010
Speech processing
➢Text to speechConverting electronic text to digital speech
➢Automatic Speech RecognitionAutomatic transcription of spoken content to electronic text
➢Speech to speech translation Translating spoken content from one language to another in real time or offline.
Govt. Eng. Collegepainav
04-06-2010
MAJOR Areas of Research & Development industrial Applications
➢Search Engines ➢Advanced Text Editors ➢Commercial Machine Translation Systems➢Information Extraction➢Collaborative filtering ➢Translation Memories ➢Computational Advertising ➢Fraud Detection ➢Sentiment Analysis➢Opinion Mining .........
Govt. Eng. Collegepainav
04-06-2010
Some examples
Document classification
Document
??Sports
ArtsHistoryScience
??
Govt. Eng. Collegepainav
04-06-2010
Information extraction
DocumentWho did what ?
When ?Where?
Barrack Obamaelected as president
Of US
Person: Barrack Obama ->WhoPosition: President -> What
Event: elected -> What
Govt. Eng. Collegepainav
04-06-2010
Sentiment analysis
#2012 in very good !!??bleh :-(
Toby Segram's ProgrammingCollective intelligence is a
nice book. It gives a detailedand simple view on ......
Govt. Eng. Collegepainav
04-06-2010
Collaborative filtering
The art /technology to make recommendations based on user behavior
Govt. Eng. Collegepainav
04-06-2010
Search engines
Govt. Eng. Collegepainav
04-06-2010
Semantic web/search
Govt. Eng. Collegepainav
04-06-2010
Future of Nlp
➢Semantic Web/Search ➢Sentiment Analysis / Opinion Mining ➢Machine Translation➢Advanced Speech Processing Application ➢Social Network Analysis➢Collective Intelligence
Govt. Eng. Collegepainav
04-06-2010
NLP in other Domains
➢Bio-Medical ➢Forensic Science➢Advertisement➢Education ➢Politics ➢E-governance ➢Business Development ➢Marketing ➢and where ever we use language !!!
Govt. Eng. Collegepainav
04-06-2010
Nlp in IndiaIIT Kanpur
IIT KharagpurIIT Delhi
IIIT HydrabadAU-KBC Chennai
C-DACMicrosoftYahooAOL
365MEEDIATaazaa
Reuters India.....
Govt. Eng. Collegepainav
04-06-2010
Discussion time
Questions ?
Govt. Eng. Collegepainav
04-06-2010
About 365media
Real time information services Started in 1998 – with 10 staff at CaliforniaIndia operations started in 2005 @ coimbatore Now 300 employees , 20 + clients
Govt. Eng. Collegepainav
04-06-2010
thanks
Jaganadh GEmail
Business [email protected] Personal [email protected]
http://jaganadhg.freeflux.net/blog