nlp final

16

Upload: anand-chafekar

Post on 26-Jan-2015

103 views

Category:

Technology


0 download

DESCRIPTION

Its started off as a part of Artificial intelligence. NLP is challenging , but its been widely researched for future application which will have human touch.

TRANSCRIPT

Page 1: Nlp final
Page 2: Nlp final

Outline What is NLP?Why Study NLP?Why are language technologies needed?Future expectationApplication areasHow NLP works?Interesting processes by NLPTools we need

Page 3: Nlp final

What is Natural Language Processing?Natural Language Processing

Processing of Human generated language. Also known as Computational Linguistics (CL),

Human Language Technology (HLT), Natural Language Engineering (NLE)

Can machines understand human language?Define ‘understand’Understanding is the ultimate goal. However,

one doesn’t need to fully understand to be useful.

Page 4: Nlp final

What does it need?

Analyze, understand and generate human languages just like humans do.

Applying computational techniques to language domain.

Started off as a branch of Artificial Intelligence..

Borrows from Linguistics, Psycholinguistics, Cognitive Science & Statistics.

Make computers learn our language rather than we learn theirs.

Page 5: Nlp final

Why Study NLP?A hallmark of human intelligence.Text is the largest repository of human

knowledge and is growing quickly.emails, news articles, web pages, IM, scientific

articles, insurance claims, customer complaint letters, transcripts of phone calls, technical documents, government documents, patent portfolios, court decisions, contracts, ……

Are we reading any faster than before?

Page 6: Nlp final

Why are language technologies needed?Many companies would make a lot of money if

they could use computer programmes that understood text or speech. Just imagine if a computer could be used for: answering the phone, and replying to a question understanding the text on a Web page to decide

who it might be of interest to translating a daily newspaper from Japanese to

English (an attempt is made to do this already) understanding text in journals / books and

building an expert systems based on that understanding

Page 7: Nlp final

Future ExpectationsShow me Star Trek..?? (Talk to your TV set)Will my computer talk to me like another human ??Will the search engine get me exactly what I am

looking for??Can my PC read the whole newspaper and tell me the

important news only..??Can my palmtop translate what that Japanese lady is

telling me.. ??Ahhh.. Can my PC do my English homework ??Do you know how our brain processes language ??

Page 8: Nlp final

Dreams??

Page 9: Nlp final

Application areasText-to-Speech & Speech recognitionNatural Language Dialogue Interfaces to Databases Information Retrieval Information ExtractionDocument ClassificationDocument Image AnalysisAutomatic SummarizationText Proofreading – Spelling & GrammarMachine TranslationStory understanding systemsPlagiarism detectionCan u think of anything else ??

Page 10: Nlp final

How NLP works

Page 11: Nlp final

NLP Processes

Excellent-Team-To train-Testing ADJ - NOUN- VERB- ADV

Named entity recognition (NER) Named entity recognition (NER)

Part –of-speech(POS) Part –of-speech(POS)

PERSON ORG LOC

Raj from TCS applied for Pune Java position

Page 12: Nlp final

Sentimental Analysis Sentimental Analysis Candidate has good technical knowledge

Poor communication skills

Word sense disambiguation (WSD) Word sense disambiguation (WSD) I need new batteries for my mouse

Information Extraction (IE) Information Extraction (IE) You have been shortlisted for F2F round

Page 13: Nlp final

Question Asking ? Question Asking ? What is a hiring strategy of IT firms for 2014? Why HR ask question like Tell me about your

self?

ABC acquired by XYZ yesterday ABC Has been taken over by

XYZ

Paraphrase Paraphrase

Summarization Summarization Good stability Experience in core

technology Immediate joining

Roll out an offer

Challenging issues

Page 14: Nlp final
Page 15: Nlp final

Tools we needKnowledge about language Knowledge about the worldA way to combine knowledge sourcesProbabilistic model built from natural

language.

Page 16: Nlp final

Thank you