Introduction to Natural Language Processing
- 1. Natural Language Processing SoSe 2016 Introduction to Natural Language Processing Dr. Mariana Neves April 11th, 2016 Introduction to Natural Language Processing http://bit.ly/2Mub6xP
- 2. Outline ● Introduction to Language ● NLP Applications ● NLP Techniques ● Linguistic Knowledge ● Challenges ● NLP course 2
- 3. Outline ● Introduction to Language ● NLP Applications ● NLP Techniques ● Linguistic Knowledge ● Challenges ● NLP course 3
- 6. Language 6 A vocabulary consists of a set of words (wi ) (http://learnenglish.britishcouncil.org/en/vocabulary-games) A text is composed of a sequence of words from a vocabulary A language is constructed of a set of all possible texts (http://www.nature.com/polopoly_fs/1.16929!/menu/main/topColumns/topLeftColumn/pdf/518273a.pdf) (http://www.old-engli.sh/language.php)
- 7. Outline ● Introduction to Language ● NLP Applications ● NLP Techniques ● Linguistic Knowledge ● Challenges ● NLP course 7
- 8. Spell and Grammar Checking ● Checking spelling and grammar ● Suggesting alternatives for the errors 8
- 9. Word Prediction ● Predicting the next word that is highly probable to be typed by the user 9
- 10. Information Retrieval ● Finding relevant information to the user’s query 10
- 11. Text Categorization ● Assigning one (or more) pre-defined category to a text 11
- 13. Summarization ● Generating a short summary from one or more documents, sometimes based on a given query 13 http://smmry.com/
- 14. Summarization 14
- 15. Question answering ● Answering questions with a short answer 15 http://start.csail.mit.edu/index.php
- 16. Question Answering & Summarization 16
- 17. Question answering ● IBM Watson in Jeopardy 17 https://www.youtube.com/watch?v=WFR3lOm_xhE
- 18. Information Extraction ● Extracting important concepts from texts and assigning them to slot in a certain template 18
- 19. Information Extraction ● Includes named-entity recognition 19 http://cogcomp.cs.illinois.edu/page/demo_view/Wikifier
- 21. Machine Translation ● Translating a text from one language to another 21
- 22. Sentiment Analysis ● Identifying sentiments and opinions stated in a text 22
- 23. Optical Character Recognition ● Recognizing printed or handwritten texts and converting them to computer-readable texts 23
- 24. Speech recognition ● Recognizing a spoken language and transforming it into a text 24
- 25. Speech synthesis ● Producing a spoken language from a text 25
- 26. Spoken dialog systems ● Running a dialog between the user and the system 26
- 28. Level of difficulties ● Easy (mostly solved) – Spell and grammar checking – Some text categorization tasks – Some named-entity recognition tasks 28
- 29. Level of difficulties ● Intermediate (good progress) – Information retrieval – Sentiment analysis – Machine translation – Information extraction 29
- 30. Level of difficulties ● Difficult (still hard) – Question answering – Summarization – Dialog systems 30
- 31. Outline ● Introduction to Language ● NLP Applications ● NLP Techniques ● Linguistic Knowledge ● Challenges ● NLP course 31
- 32. Section splitting ● Splitting a text into sections 32
- 33. Sentence splitting ● Splitting a text into sentences 33
- 34. Part-of-speech tagging ● Assigning a syntatic tag to each word in a sentence 34 http://nlp.stanford.edu:8080/corenlp/
- 35. Parsing ● Building the syntactic tree of a sentence 35 http://nlp.stanford.edu:8080/corenlp/
- 36. Parsing ● Building the syntactic tree of a sentence 36 http://nlp.stanford.edu:8080/corenlp/
- 37. Named-entity recognition ● Identifying pre-defined entity types in a sentence 37
- 38. Word sense disambiguation ● Figuring out the exact meaning of a word or entity 38 http://www.thefreedictionary.com/tie
- 41. Semantic role labeling ● Extracting subject-predicate-object triples from a sentence 41 http://cogcomp.cs.illinois.edu/page/demo_view/srl
- 42. Outline ● Introduction to Language ● NLP Applications ● NLP Techniques ● Linguistic Knowledge ● Challenges ● NLP course 42
- 43. Phonetics and phonology ● The study of linguistic sounds and their relations to words 43 http://german.about.com/library/blfunkabc.htm
- 44. Morphology ● The study of internal structures of words and how they can be modified ● Parsing complex words into their components 44 (http://allthingslinguistic.com/post/50939757945/morphological-typology-illustrations-from)
- 45. Syntax ● The study of the structural relationships between words in a sentence 45
- 46. Semantics ● The study of the meaning of words, and how these combine to form the meanings of sentences – Synonymy: fall & autumn – Hypernymy & hyponymy (is a): animal & dog – Meronymy (part of): finger & hand – Homonymy: fall (verb & season) – Antonymy: big & small 46
- 47. Pragmatics ● Social use of language ● The study of how language is used to accomplish goals, and the influence of context on meaning ● Understanding the aspects of a language which depends on situation and world knowledge 47 Give me the salt! Could you please give me the salt?
- 48. Discourse ● The study of linguistic units larger than a single statement 48 John reads a book. He borrowed it from his friend. (http://en.wikipedia.org/wiki/Berlin)
- 49. Outline ● Introduction to Language ● NLP Applications ● NLP Techniques ● Linguistic Knowledge ● Challenges ● NLP course 49
- 50. Paraphrasing ● Different words/sentences express the same meaning – Season of the year ● Fall ● Autumn – Book delivery time ● When will my book arrive? ● When will I receive my book? 50
- 51. Ambiguity ● One word/sentence can have different meanings – Fall ● The third season of the year ● Moving down towards the ground or towards a lower position – The door is open. ● Expressing a fact ● A request to close the door 51
- 53. Syntax and ambiguity ● I saw the man with a telescope. – Who had the telescope? 53 (http://www.realtytrac.com/landing/2009-year-end-foreclosure-report.html)
- 54. Semantics ● The astronomer loves the star. – Star in the sky – Celebrity 54 (http://www.businessnewsdaily.com/2023-celebrity-hiring.html) (http://en.wikipedia.org/wiki/Star#/media/File:Starsinthesky.jpg)
- 55. Discourse analysis ● Alice understands that you like your mother, but she … – Does she refer to Alice or your mother? 55
- 56. Outline ● Introduction to Language ● NLP Applications ● NLP Techniques ● Linguistic Knowledge ● Challenges ● NLP course 56
- 57. NLP Course ● Home page: – http://hpi.de/plattner/teaching/summer-term- 2016/natural-language-processing.html ● Lecture – – HS3 – 3 credit points 57 http://bit.ly/2Mub6xP NLP for Machine Learning Featuring Label Encoding One hot encoding Synonym treatment Stemming Lemmatization Stop words Parts Of Speech Tagging TF-IDF and its math Behind