NLP_lectures_English

Introduction to Natural Language Processingin 3 Sessions

Dr. Alexandra M. Liguori

Incubio – The Big Data Academy

Barcelona, March - April, 2015

Dr. Alexandra M. Liguori Introduction to Natural Language Processing in 3 Sessions

Outline: Lecture 1

1 Introduction2 Natural Language Processing3 Linguistic Ambiguities4 Definition of corpus5 Typical NLP tasks6 POS-tagging

Outline: Lecture 2

1 Recap: Typical NLP tasks → practical examples with GATE2 Def. of semantics3 Frames approach

1 FrameNet2 GATE for semantic/content analysis

Outline: Lecture 3

1 Recap: Typical NLP tasks2 Automatic Question Answering3 Reference resolution4 Named Entity Recognition (NER)5 Keyword / topic / information extraction

Welcome!

Here we go...!!!

Main references:

Text book: Speech and Language Processing by D. Jurafskyand J. H. Martin

English FrameNet: https://framenet.icsi.berkeley.edu/fndrupal/

Spanish FrameNet: http://sfn.uab.es:8080/SFN

GATE: https://gate.ac.uk/

Outline: Lecture 1

1 Introduction2 Natural Language Processing3 Linguistic Ambiguities4 Definition of corpus5 Typical NLP tasks6 POS-tagging

Introduction: Intelligent machines?

Video:https://www.youtube.com/watch?v=dSIKBliboIo

(Stanley Kubrick and Arthur C. Clarke,screenplay of 2001: A Space Odyssey )

Dave Bowman: Open the pod bay doors, HAL.

HAL: I’m sorry Dave, I’m afraid I can’t do that.

(Stanley Kubrick and Arthur C. Clarke,screenplay of 2001: A Space Odyssey )

https://www.youtube.com/watch?v=dSIKBliboIo

1 Phonetics and phonology2 Morphology → produce contractions I’m and can’t3 Syntax → cfr. Open the pod bay doors, HAL.

vs. HAL, the pod bay door is open.vs. HAL, is the pod bay door open?

4 Lexical semantics → meaning of component words5 Compositional semantics → knowledge of how

components combine to form larger meanings6 Pragmatics → cfr. I’m sorry ... , I’m afraid I can’t

vs. No, I won’t open the door.vs. No.

7 Discourse conventions → engaging in structuredconversation using reference that in I’m sorry Dave, I’mafraid I can’t do that

1 Phonetics and phonology

2 Morphology → produce contractions I’m and can’t3 Syntax → cfr. Open the pod bay doors, HAL.

1 Phonetics and phonology2 Morphology → produce contractions I’m and can’t

3 Syntax → cfr. Open the pod bay doors, HAL.vs. HAL, the pod bay door is open.vs. HAL, is the pod bay door open?

4 Lexical semantics → meaning of component words

5 Compositional semantics → knowledge of howcomponents combine to form larger meanings

6 Pragmatics → cfr. I’m sorry ... , I’m afraid I can’tvs. No, I won’t open the door.vs. No.

components combine to form larger meanings

6 Pragmatics → cfr. I’m sorry ... , I’m afraid I can’tvs. No, I won’t open the door.vs. No.

Natural Language Processing

NLP: techniques that process written human language aslanguage.

Applicationsword countingautomatic hyphenationautomated question answeringnamed entity extraction (NER)information/content extractionsemantic analysissentiment analysismachine translation

An ideal NLP team is very interdisciplinary, including:Language experts (linguists)Maths experts (mathematicians, physicists, statisticians)Programmers (computer scientists)

NLP: Maths & Computer Science

NLP: Six categories of linguistic knowledge

1 Phonetics and phonology ↔ red - read - read ;sleigh - slay

2 Morphology ↔ I/you/we/you/they walk - he/she/it walks;walked; walking

3 Syntax ↔ She ate a mammoth breakfast - She eating amammoth breakfast

4 Semantics ↔ book (verb) - book (noun);duck (verb) - duck (noun)

5 Pragmatics ↔ open the door - can you open the door? -could you open the door, please?

6 Discourse

Gracie: Oh yeah... And then Mr. and Mrs. Jones werehaving matrimonial trouble, and my brother was hired towatch Mrs. Jones.George: Well, I imagine she was a very attractive woman.Gracie: She was, and my brother watched her day andnight for six months.George: Well, what happened?Gracie: She finally got a divorce.George: Mrs. Jones?Gracie: No, my brother’s wife.

John went to Bill’s car dealership to check out anAcura Integra. He looked at it for about an hour.

6 DiscourseGracie: Oh yeah... And then Mr. and Mrs. Jones werehaving matrimonial trouble, and my brother was hired towatch Mrs. Jones.George: Well, I imagine she was a very attractive woman.Gracie: She was, and my brother watched her day andnight for six months.George: Well, what happened?Gracie: She finally got a divorce.George: Mrs. Jones?Gracie: No, my brother’s wife.

NLP: Ambiguities and Solutions

Linguistic Ambiguities

ExampleI made her duck.

Five possible interpretations:

1 I cooked waterfowl for her.2 I cooked waterfowl belonging to her.3 I created the (plaster?) duck she owns.4 I caused her to quickly lower her head or body.5 I waved my magic wand and turned her into

undifferentiated waterfowl.

1 I cooked waterfowl for her.

2 I cooked waterfowl belonging to her.3 I created the (plaster?) duck she owns.4 I caused her to quickly lower her head or body.5 I waved my magic wand and turned her into

1 I cooked waterfowl for her.2 I cooked waterfowl belonging to her.

3 I created the (plaster?) duck she owns.4 I caused her to quickly lower her head or body.5 I waved my magic wand and turned her into

1 I cooked waterfowl for her.2 I cooked waterfowl belonging to her.3 I created the (plaster?) duck she owns.

4 I caused her to quickly lower her head or body.5 I waved my magic wand and turned her into

1 I cooked waterfowl for her.2 I cooked waterfowl belonging to her.3 I created the (plaster?) duck she owns.4 I caused her to quickly lower her head or body.

5 I waved my magic wand and turned her intoundifferentiated waterfowl.

Morphological ambiguityduck : verb or nounher : dative pronoun or possessive pronoun

Syntactic ambiguity: make

transitive: taking a single direct object (case 2)ditransitive: taking two objects, meaning that the first object(her ) got made into the second object (duck )taking a direct object and a verb, meaning that the object(her ) got caused to perform the verbal action (duck )

Semantic ambiguity: makecookcreate

Corpus

DefinitionCorpus = Large and structured set of texts.

NLPTwo types of corpora:

Training corpus ↔ to make the list of rules or to get thestatistical dataTest corpus ↔ to test the results found with the trainingcorpus

Corpus

DefinitionCorpus = Large and structured set of texts.

NLPTwo types of corpora:

Training corpus ↔ to make the list of rules or to get thestatistical dataTest corpus ↔ to test the results found with the trainingcorpus

Typical NLP tasks: Basic and simpler tasks

Tokenization RegEx

Sentence splitting RegEx

POS-tagging POS-tagging algorithms andtag sets

Tokenization

Tokenization RegEx

Sentence splitting

Tokenization RegEx

POS-tagging

POS-tagging algorithms andtag sets

Tokenization RegEx

Typical NLP tasks: Complex tasks

Lemmatization or StemmingImplementations of PorterStemmer (e.g. in Java),

Stanford NLP tool, GATE, ...

Syntactic parsing

Early algorithm, CYKalgorithm, GHR algorithm,

Stanford Parser (Javaimplementation of

probabilistic algorithm)

Topic extractionNERSemantic analysis...

Ad hoc tools, e.g.dictionaries, ontologies,Frames, GATE, NLTK,

Lemmatization or Stemming

Implementations of PorterStemmer (e.g. in Java),

Syntactic parsing

POS-tagging

Example with Penn Treebank POS-tags:

A/DT woman/NN came/VBD from/IN the/DT back/NN of/INthe/DT store/NN ./. She/PP appeared/VBD to/TO be/VB

sleepy/JJ and/CC quite/RB a/DT bit/NN younger/JJR than/INMr./NNP Dobbs/NNP and/CC to/TO be/VB wearing/VBG

too/RB much/RB makeup/NN ./.

POS-tagging

Example of ambiguity:

1 Secretariat/NNP is/VBZ expected/VBN to/TO race/VBtomorrow/NN ./.

2 People/NNS continue/VBP to/TO inquire/VB the/DTreason/NN for/IN the/DT race/NN for/IN outer/JJ space/NN./.

POS-tagging

Example of ambiguity:1 Secretariat/NNP is/VBZ expected/VBN to/TO race/VB

tomorrow/NN ./.

POS-tagging

tomorrow/NN ./.

POS-tagging

Three main tagging algorithms or methods:1 rule-based tagging, e.g. ENGTWOL2 stochastic tagging, e.g. HMM tagger3 transformation-based tagging, e.g. Brill tagger

Rule-based POS-tagging

tomorrow/NN ./.2 People/NNS continue/VBP to/TO inquire/VB the/DT

reason/NN for/IN the/DT race/NN for/IN outer/JJ space/NN./.

Large database of hand-written disambiguation rules, e.g.:

TO + VB → YESTO + NN → NODT + NN → YESDT + VB → NO

Large database of hand-written disambiguation rules, e.g.:TO + VB → YESTO + NN → NODT + NN → YESDT + VB → NO

Stochastic POS-tagging

Training corpus to compute probability of given word havinggiven tag in given context, e.g.:

is/VBZ expected/VBN to/TO race/VB → 98%

is/VBZ expected/VBN to/TO race/NN → 2%

reason/NN for/IN the/DT race/NN → 97%

reason/NN for/IN the/DT race/VB → 3%

Transformation-based tagging POS-tagging

Secretariat/NNP is/VBZ expected/VBN to/TO race/VBtomorrow/NN ./.People/NNS continue/VBP to/TO inquire/VB the/DTreason/NN for/IN the/DT race/NN for/IN outer/JJ space/NN

Rules automatically induced from data using Machine Learningtechniques, e.g.:

1 a priori, prob(race = NN)= 65%, prob(race = VB)= 35%→ system would always take race = NN

2 Machine Learning to learn conditional probabilities:3 is/VBZ expected/VBN to/TO race/VB → 98%

reason/NN for/IN the/DT race/NN → 97%4 system takes race = NN or race = VB depending on

context.

2 Machine Learning to learn conditional probabilities:

3 is/VBZ expected/VBN to/TO race/VB → 98%reason/NN for/IN the/DT race/NN → 97%

4 system takes race = NN or race = VB depending oncontext.

context.

POS-tagging

POS-tagging tools for English:Brill taggerStanford Log-linear POS-tagger (Java)POS-tagger integrated in GATE (Java)POS-tagger with NLTK (Python)

Outline: Lecture 2

1 Recap: Typical NLP tasks → practical examples with GATE2 Def. of semantics3 Frames approach

1 FrameNet2 GATE for semantic/content analysis

Tokenization RegEx

Tokenization

Tokenization RegEx

Sentence splitting

Tokenization RegEx

POS-tagging

Tokenization RegEx

Ad hoc tools, e.g.dictionaries, ontologies,Frames, GATE, NLTK, ...

EX.: GATE

Concrete examples with GATE:1 Tokenizer2 Sentence-splitter3 POS-tagger4 Stemmer

GATEhttps://gate.ac.uk/

development at the University of Sheffield, UK.

EX.: GATE

Concrete examples with GATE:1 Tokenizer2 Sentence-splitter3 POS-tagger4 Stemmer

Semantics

’Then you should say what you mean,’the March Hare went on.’I do,’ Alice hastily replied;

’at least, I mean what I say –that’s the same thing, you know.’

’Not the same thing a bit!’ said the Hatter. ’You might just aswell say that

”I see what I eat” is the same thing as ”I eat what I see”! ’

Lewis Carroll,Alice in Wonderland

Frames and FrameNet

FrameA schematic representation of a situation involving various

participants, and other conceptual roles.E.g.:

Abby bought a car from Robin for $5,000.Robin sold a car to Abby for $5,000.

English FrameNet

https://framenet.icsi.berkeley.edu/fndrupal/development at the International Computer Science Institute in

Berkeley, California.

Frames and FrameNet

participants, and other conceptual roles.E.g.:

Abby bought a car from Robin for $5,000.Robin sold a car to Abby for $5,000.

English FrameNet

https://framenet.icsi.berkeley.edu/fndrupal/development at the International Computer Science Institute in

Berkeley, California.

English FrameNet Example

Frame Relations

FrameNet additionally captures relationships between differentframes using relations. These include the following:

Inheritance: When one frame is a more specific version ofanother, more abstract parent frame. Anything that is trueabout the parent frame must also be true about the childframe, and a mapping is specified between the frameelements of the parent and the frame elements of the child.Perspectivized-in: A neutral frame (likeCommerce-transfer-goods) is connected to a frame with aspecific perspective of the same scenario (e.g. theCommerce-sell frame, which assumes the perspective ofthe seller or the Commerce-buy frame, which assumes theperspective of the buyer)Subframe: Some frames like the Criminal-process framerefer to complex scenarios that consist of several individualstates or events that can be described by separate frameslike Arrest, Trial, and so on.

Frame Relations

Precedes: The Precedes relation captures a temporalorder that holds between subframes of a complex scenario.Causative-of and Inchoative-of : There is a fairly systematicrelationship between stative descriptions (e.g. thePosition-on-a-scale frame, "She had a high salary") andcausative descriptions (Cause-change-of-scalar-position,"She raised his salary") or inchoative descriptions(Change-position-on-a-scale, e.g. "Her salary increased").Using: A relationship that holds between a frame that insome way involves another frame. For instance, theJudgment-communication frame uses both the Judgmentframe and the Statement frame, but does not inherit fromeither of them because there is no clear correspondence ofthe frame elements.See-also: Connects frames that bear some resemblancebut need to be distinguished carefully.

Spanish FrameNet

participants, and other conceptual roles. E.g.:El rock influye en los artistas de hoy en díapara sus producciones artísticas.Los artistas de hoy en día se inspiran al rockpara sus producciones artísticas.

Spanish FrameNethttp://sfn.uab.es:8080/SFN

development at the Universidad Autónoma de Barcelona andInternational Computer Science Institute in Berkeley, California.

Spanish FrameNet

participants, and other conceptual roles. E.g.:El rock influye en los artistas de hoy en díapara sus producciones artísticas.Los artistas de hoy en día se inspiran al rockpara sus producciones artísticas.

Spanish FrameNethttp://sfn.uab.es:8080/SFN

development at the Universidad Autónoma de Barcelona andInternational Computer Science Institute in Berkeley, California.

Spanish FrameNet Example

Frames and GATE

And now...Ex. in English implementing FRAMES, LUs, and FEs with

GATE !!!

Frames and GATE

And now...Ex. in English implementing FRAMES, LUs, and FEs with

GATE !!!

Outline: Lecture 3

1 Recap: Typical NLP tasks2 Automatic Question Answering3 Reference resolution4 Named Entity Recognition (NER)5 Keyword / topic / information extraction

Tokenization RegEx

Tokenization

Tokenization RegEx

Sentence splitting

Tokenization RegEx

POS-tagging

Tokenization RegEx

Syntactic parsing

Question answeringTopic extractionNERSemantic analysis...

Syntactic parsing

Question Answering

Example from Who’s on first

Question Answering

Simple Question Answering

ELIZAELIZA simulated a Rogerian psychologist, and could carry on

conversations with the user like the following:

User-1: Men are all alike.ELIZA-1: IN WHAT WAY

User-2: They’re always bugging us about something or other..ELIZA-2: CAN YOU THINK OF A SPECIFIC EXAMPLE

User-3: Well, my boyfriend made me come here.ELIZA-3: YOUR BOYFRIEND MADE YOU COME HERE

User-4: Yes, he says I’m depressed much of the time.ELIZA-4: I AM SORRY TO HEAR YOU ARE DEPRESSED.

Regular expression substitutionsEliza worked by having a cascade of regular expression substitutionsthat each matched some part of the input lines and changed them:

change all instances of my to YOUR, and I’m to YOU ARE, etc.,e.g.:

1 User-3: Well, my boyfriend made me come here.ELIZA-3: YOUR BOYFRIEND MADE YOU COME HERE

2 User-4: ... I’m depressed ... .ELIZA-4: ... YOU ARE DEPRESSED.

relevant patterns in the input → creat an appropriate output;e.g.:

1 s/.* YOU ARE (depressed | sad) .*/I AM SORRY TO HEARYOU ARE \1 /

2 s/.* YOU ARE (depressed | sad) .*/WHY DO YOU THINKYOU ARE \1 /

3 s/.* all .*/IN WHAT WAY/4 s/.* always .*/CAN YOU THINK OF A SPECIFIC EXAMPLE/

3 s/.* all .*/IN WHAT WAY/

4 s/.* always .*/CAN YOU THINK OF A SPECIFIC EXAMPLE/

Reference resolution

Discourse

Gracie: Oh yeah... And then Mr. and Mrs. Jones were havingmatrimonial trouble, and my brother was hired to watch Mrs. Jones.George: Well, I imagine she was a very attractive woman.Gracie: She was, and my brother watched her day and night for sixmonths.George: Well, what happened?Gracie: She finally got a divorce.George: Mrs. Jones?Gracie: No, my brother’s wife.

John went to Bill’s car dealership to check out an Acura Integra.He looked at it for about an hour.

Discourse

1 Reference phenomena2 Constraints on coreference3 Preferences in pronoun interpretation4 Example of algorithm for pronoun resolution

1 Reference phenomena

2 Constraints on coreference3 Preferences in pronoun interpretation4 Example of algorithm for pronoun resolution

1 Reference phenomena2 Constraints on coreference

3 Preferences in pronoun interpretation4 Example of algorithm for pronoun resolution

1 Reference phenomena2 Constraints on coreference3 Preferences in pronoun interpretation

4 Example of algorithm for pronoun resolution

1 Reference phenomena2 Constraints on coreference3 Preferences in pronoun interpretation4 Example of algorithm for pronoun resolution

Reference phenomena

1 Indefinite noun phrases ↔ I saw an Honda Civic today.2 Definite noun phrases ↔ I saw an Honda Civic today.

The Honda Civic was blue.3 Pronouns ↔ I saw an Honda Civic today. It was blue.4 Demonstratives ↔ I bought an Honda Civic today. It’s

similar to the one I bought five years ago. That one wasreally nice, but I like this one even better.

5 One-anaphora ↔ I saw no less than 6 Honda Civicstoday. Now I want one.

Reference phenomena1 Indefinite noun phrases ↔ I saw an Honda Civic today.

2 Definite noun phrases ↔ I saw an Honda Civic today.The Honda Civic was blue.

3 Pronouns ↔ I saw an Honda Civic today. It was blue.4 Demonstratives ↔ I bought an Honda Civic today. It’s

Reference phenomena1 Indefinite noun phrases ↔ I saw an Honda Civic today.2 Definite noun phrases ↔ I saw an Honda Civic today.

The Honda Civic was blue.

3 Pronouns ↔ I saw an Honda Civic today. It was blue.4 Demonstratives ↔ I bought an Honda Civic today. It’s

The Honda Civic was blue.3 Pronouns ↔ I saw an Honda Civic today. It was blue.

4 Demonstratives ↔ I bought an Honda Civic today. It’ssimilar to the one I bought five years ago. That one wasreally nice, but I like this one even better.

Constraints on coreference

1 number agreement ↔ John has a new car. It is red. /John has a new car. They are red.

2 person and case agreement ↔ John and Mary have newcars. They love them.

3 gender agreement ↔ John has a new car. It is attractive./ John has a new car. He is attractive.

4 syntactic constraints ↔ John bought himself a new car. /John bought him a new car.

5 selectional restrictions ↔ John parked his car in thegarage. He had driven it around for hours.

Constraints on coreference1 number agreement ↔ John has a new car. It is red. /

John has a new car. They are red.

2 person and case agreement ↔ John and Mary have newcars. They love them.

John has a new car. They are red.2 person and case agreement ↔ John and Mary have new

cars. They love them.

cars. They love them.3 gender agreement ↔ John has a new car. It is attractive.

/ John has a new car. He is attractive.

/ John has a new car. He is attractive.4 syntactic constraints ↔ John bought himself a new car. /

John bought him a new car.

/ John has a new car. He is attractive.4 syntactic constraints ↔ John bought himself a new car. /

John bought him a new car.5 selectional restrictions ↔ John parked his car in the

garage. He had driven it around for hours.

Preferences in pronoun interpretation

1 recency ↔ Peter has an Audi. Bob has a Honda. Annelikes to drive it.

2 grammatical role ↔ Peter went to the Honda dealershipwith Bob. He bought a Civic. / Bob went to the Hondadealership with Peter. He bought a Civic.

3 repeated mention ↔ Anne needed a car to drive to hernew job. She decided she wanted something roomy. Carolwent to the Honda dealership with her. She bought a Civic.

4 parallelism ↔ Anne went with Carol to the Hondadealership. Sally went with her to the VW dealership.

5 verb semantics ↔ Peter seized the Honda pamphlet fromBob. He loves reading about cars. / Peter passed theHonda pamphlet to Bob. He loves reading about cars.

Preferences in pronoun interpretation1 recency ↔ Peter has an Audi. Bob has a Honda. Anne

likes to drive it.

2 grammatical role ↔ Peter went to the Honda dealershipwith Bob. He bought a Civic. / Bob went to the Hondadealership with Peter. He bought a Civic.

likes to drive it.2 grammatical role ↔ Peter went to the Honda dealership

with Bob. He bought a Civic. / Bob went to the Hondadealership with Peter. He bought a Civic.

Named Entity Recognition

Can be broken down in two distinct problems, i.e.:

1 detection of names2 classification of the names by the type of entity to which

they refer → 4 standard types:1 person (e.g. ”Carol”, ”Tom Hanks”, etc.)2 organization (e.g. ”WWF”, IBM”, ”Bank of America”, etc.)3 location (e.g. ”London”, "Washington D.C.”, ”L.A.”,

”Barcelona”, etc.)4 other (e.g. ”Hotel Sunshine”, etc. )

Can be broken down in two distinct problems, i.e.:

1 detection of names2 classification of the names by the type of entity to which

Can be broken down in two distinct problems, i.e.:1 detection of names

2 classification of the names by the type of entity to whichthey refer → 4 standard types:

1 person (e.g. ”Carol”, ”Tom Hanks”, etc.)2 organization (e.g. ”WWF”, IBM”, ”Bank of America”, etc.)3 location (e.g. ”London”, "Washington D.C.”, ”L.A.”,

Can be broken down in two distinct problems, i.e.:1 detection of names2 classification of the names by the type of entity to which

they refer → 4 standard types:

1 person (e.g. ”Carol”, ”Tom Hanks”, etc.)2 organization (e.g. ”WWF”, IBM”, ”Bank of America”, etc.)3 location (e.g. ”London”, "Washington D.C.”, ”L.A.”,

they refer → 4 standard types:1 person (e.g. ”Carol”, ”Tom Hanks”, etc.)

2 organization (e.g. ”WWF”, IBM”, ”Bank of America”, etc.)3 location (e.g. ”London”, "Washington D.C.”, ”L.A.”,

they refer → 4 standard types:1 person (e.g. ”Carol”, ”Tom Hanks”, etc.)2 organization (e.g. ”WWF”, IBM”, ”Bank of America”, etc.)

3 location (e.g. ”London”, "Washington D.C.”, ”L.A.”,”Barcelona”, etc.)

4 other (e.g. ”Hotel Sunshine”, etc. )

”Barcelona”, etc.)

4 other (e.g. ”Hotel Sunshine”, etc. )

Tools for Named Entity RecognitionGATE for English, Spanish, and many more, via graphicalinterface and Java API (development at the University ofSheffield, UK)https://gate.ac.uk/NETagger: Java based Illinois Named Entity Recognition(development by Cognitive Computation Group at University ofIllinois at Urbana - Champaign)http://cogcomp.cs.illinois.edu/page/software_view/NETaggerOpenNLP: rule based and statistical Named Entity Recognition(development by Apache)http://opennlp.apache.org/index.htmlStanford CoreNLP: Java-based CRF Named Entity Recognition(development by Stanford Natural Language Processing Group)http://nlp.stanford.edu/software/CRF-NER.shtml

Keyword / topic / information extraction

ToolsKeyword extraction: e.g. GATE (ANNIE tool) for English,Spanish, and many more, via graphical interface and JavaAPI→ simply using jape files for the LUstool from Volker ?Topic / information extraction: e.g. GATE (ANNIE tool)for English, Spanish, and many more, via graphicalinterface and Java API→ using jape files for the LUs, FEs, and FRAMES

development at the University of Sheffield, UK

Thank you for your attention!

For more information:

Example text book: Speech and Language Processingby D. Jurafsky and J. H. Martin

Web page: www.alexandramliguoriphd.com

Linkedin profile: Alexandra M. Liguori, Ph.D.

NLP_lectures_English

Documents

Transcript of NLP_lectures_English