Example

Download Report

Transcript Example - Instytut Matematyczny, Uniwersytet Wrocławski

Computational Linguistics

Dragomir Radev Wroc ław, Poland July 29, 2009

Example (from a famous movie)

Dave Bowman: Open the pod bay doors, HAL.

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

Instructor

• • Dragomir Radev, Professor, Computer Science and Information, Linguistics, University of Michigan [email protected]

Natural Language Understanding

• … about teaching computers to make sense of naturally occurring text.

• … involves programming, linguistics, artificial intelligence, etc.

• …includes machine translation, question answering, dialogue systems, database access, information extraction, game playing, etc.

I saw her fall

• How many different interpretations does the above sentence have? How many of them are reasonable/grammatical?

Silly sentences

• Children make delicious snacks • Stolen painting found by tree • I saw the Grand Canyon flying to New York • Court to try shooting defendant • Ban on nude dancing on Governor’s desk • Red tape holds up new bridges • Iraqi head seeks arms • Blair wins on budget, more lies ahead • Local high school dropouts cut in half • Hospitals are sued by seven foot doctors • In America a woman has a baby every 15 minutes. How does she do that?

Types of ambiguity

• • • • • • • • • • • • • • Morphological: Joe is quite impossible. Joe is quite important.

Phonetic: Joe’s finger got number.

Part of speech: Joe won the first round.

Syntactic: Call Joe a taxi.

Pp attachment: Joe ate pizza with a fork. Joe ate pizza with meatballs. Joe ate pizza with Mike. Joe ate pizza with pleasure.

Sense: Joe took the bar exam.

Modality: Joe may win the lottery.

Subjectivity: Joe believes that stocks will rise.

Scoping: Joe likes ripe apples and pears.

Negation: Joe likes his pizza with no cheese and tomatoes.

Referential: Joe yelled at Mike. He had broken the bike.

Joe yelled at Mike. He was angry at him.

Reflexive: John bought him a present. John bought himself a present.

Ellipsis and parallelism: Joe gave Mike a beer and Jeremy a glass of wine.

Metonymy: Boston called and left a message for Joe.

• • • • • • • • • • • • • • • • • •

NLP

Information extraction Named entity recognition Trend analysis Subjectivity analysis Text classification Anaphora resolution, alias resolution Cross-document crossreference Parsing Semantic analysis Word sense disambiguation Word clustering Question answering Summarization Document retrieval (filtering, routing) Structured text (relational tables) Paraphrasing and paraphrasing/entailment ID Text generation Machine translation

Syntactic categories

• Substitution test:

Nathalie likes cats. tabby small easy to raise

• Open (lexical) and closed (functional) categories:

No-fly-zone yadda yadda yadda the in

Jabberwocky (Lewis Carroll)

Twas brillig, and the slithy toves Did gyre and gimble in the wabe: All mimsy were the borogoves, And the mome raths outgrabe.

"Beware the Jabberwock, my son!

The jaws that bite, the claws that catch!

Beware the Jubjub bird, and shun The frumious Bandersnatch!"

Phrase structure

S NP VP

That man

VBD NP PP

caught the butterfly

with a

net

Sample phrase-structure grammar

S  NP  NP  NP  VP  VP  VP  P  NP VP AT NNS AT NN NP PP VP PP VBD VBD NP IN NP AT  NNS  NNS  NNS  VBD  VBD  VBD  IN  IN  NN 

the children students mountains slept ate saw in of cake

Phrase structure grammars

• Local dependencies • Non-local dependencies • Subject-verb agreement

The women who found the wallet were given a reward.

• wh-extraction

Should Peter buy a book?

Which book should Peter buy?

• Empty nodes

Subcategorization

Subject: The

children

eat candy.

Object: The children eat

candy

Prepositional phrase: She put the book

on the table

Predicative adjective: We made the man

angry

Bare infinitive: She helped me

walk

To-infinitive: She likes

to walk

Participial phrase: She stopped

singing that tune

at the end.

That-clause: She thinks

that it will rain tomorrow

Question-form clauses: She asked me

what book I was reading

Phrase structure ambiguity

• Grammars are used for generating and parsing sentences • Parses • Syntactic ambiguity • Attachment ambiguity:

Our company is training workers.

•

The children ate the cake with a spoon

• High vs. low attachment • Garden path sentences:

The horse raced past the barn fell. Is the book on the table red?

Sentence-level constructions

• Declarative vs. imperative sentences • Imperative sentences:



• • Yes-no questions:



-type questions:



Aux NP VP Wh-NP VP

• Fronting (less frequent): On Tuesday, I would like to fly to San Diego

Semantics and pragmatics

• Lexical semantics and compositional semantics • Hypernyms, hyponyms, antonyms, meronyms and holonyms (part-whole relationship, tire is a meronym of car), synonyms, homonyms • Senses of words, polysemous words • Homophony (

bass

• Collocations:

white hair

white wine

• Idioms:

to kick the bucket

Discourse analysis

• Anaphoric relations:

1. Mary helped Peter get out of the car. He thanked her.

2. Mary helped the other passenger out of the car. The man had asked her for help because of his foot injury.

• Information extraction problems (entity crossreferencing)

Hurricane Hugo destroyed 20,000 Florida homes.

At an estimated cost of one billion dollars, the disaster has been the most costly in the state’s history.

Pragmatics

• The study of how knowledge about the world and language conventions interact with literal meaning.

• Speech acts • Research issues: resolution of anaphoric relations, modeling of speech acts in dialogues

Coordination

• Coordinate noun phrases: –



NP and NP

–



S and S

– Similar for VP, etc.

Agreement

• Examples: – Do any flights stop in Chicago?

– Do I get dinner on this flight?

– Does Delta fly from Atlanta to Boston?

– What flights leave in the morning?

– * What flight leave in the morning?

• Rules: – S 

Aux NP VP

– S  – S – 

3sgAux 3sgNP VP Non3sgAux Non3sgNP VP 3sgAux

 does | has | can … –

non3sgAux

 do | have | can …

Agreement

• We now need similar rules for pronouns, also for number agreement, etc.

– 3SgNP  SgNominal (Det) (Card) (Ord) (Quant) (AP) – Non3SgNP  (Det) (Card) (Ord) (Quant) (AP) PlNominal – SgNominal  SgNoun | SgNoun SgNoun – etc.

Combinatorial explosion

• What other phenomena will cause the grammar to expand?

• Solution: parameterization with feature structures (see Chapter 11)

Parsing as search

Parsing as search

Book that flight.

Two types of constraints on the parses: a) some that come from the input string, b) others that come from the grammar S VP NP Verb Book Det that Nom Noun flight

NP S

Top-down parsing

S VP S Aux NP VP S VP S S S S S NP VP Det Nom NP VP Aux NP VP Aux NP VP PropN Det Nom PropN VP V NP S VP V

Bottom-up parsing

Noun Book Det that Noun flight Book that flight Verb Book Det that Noun flight NOM Noun Book Det that NP NOM Noun flight NOM Noun Book Det that NOM Noun flight VP Verb Book Det that Verb Book NOM Noun flight Det that VP VP Verb Book Det that NP NOM Noun flight Verb Book NOM Noun flight Verb Book Det that NP NOM Noun flight Det that NP NOM Noun flight

Grammatical Relations and Free Ordering of Subject and Object SVO

Кого

увидел Вася?

Вася увидел

Машу

Who

did Vasya see?

- Vasya saw

Masha

OSV

Кого же

Вася увидел?.

Машу

Вася увидел.

VSO Увидел Вася кого? Увидел Вася

Машу .

- (Actually,) - Vasya saw

who

did Vasya see?

Masha Who

did Vasya see?

- Vasya saw

Masha

SOV

Кого же

Вася увидел?

Вася

Машу

увидел -

Who

did Vasya see?

- Vasya saw Masha OVS Да кого увидел Вася?

Машу

увидел Вася - Well, whom did Vasya see?

- It was Masha whom Vasya saw.

VOS Увидел Машу кто?

Увидел Машу Вася.

Who

saw Masha, at the end?

It was Vasya who saw Masha Slide from Lori Levin, originally by Leonid Iomdin

Features and unification

• Grammatical categories have properties • Constraint-based formalisms • Example:

this flights

: agreement is difficult to handle at the level of grammatical categories • Example:

many water

: count/mass nouns • Sample rule that takes into account features:

 NP VP (but only if the number of the NP is equal to the number of the VP)

Feature structures

CAT NP NUMBER SINGULAR PERSON 3 CAT NP AGREEMENT NUMBER SG PERSON 3 Feature paths: {x agreement number}

Unification

[NUMBER SG] [NUMBER SG] + [NUMBER SG] [NUMBER PL] [NUMBER SG] [NUMBER []] = [NUMBER SG] [NUMBER SG] [PERSON 3] = ?

Agreement

• S  NP VP {NP AGREEMENT} = {VP AGREEMENT} • Does this flight serve breakfast?

• Do these flights serve breakfast?

• S  Aux NP VP {Aux AGREEMENT} = {NP AGREEMENT}

Agreement

• These flights • This flight • NP  Det Nominal {Det AGREEMENT} = {Nominal AGREEMENT} • Verb  serve {Verb AGREEMENT NUMBER} = PL • Verb  serves {Verb AGREEMENT NUMBER} = SG

Subcategorization

• VP  Verb {VP HEAD} = {Verb HEAD} {VP HEAD SUBCAT} = INTRANS • VP  Verb NP {VP HEAD} = {Verb HEAD} {VP HEAD SUBCAT} = TRANS • VP  Verb NP NP {VP HEAD} = {Verb HEAD} {VP HEAD SUBCAT} = DITRANS

Eliza [Weizenbaum, 1966]

User: Men are all alike ELIZA: IN WHAT WAY User: They’re always bugging us about something or other ELIZA: CAN YOU THINK OF A SPECIFIC EXAMPLE?

User: Well, my boyfriend made me come here ELIZA: YOUR BOYFRIEND MADE YOU COME HERE User: He says I’m depressed much of the time ELIZA: I AM SORRY TO HEAR THAT YOU ARE DEPRESSED

Eliza-style regular expressions

Step 1: replace first person references with second person references Step 2: use additional regular expressions to generate replies Step 3: use scores to rank possible transformations s/.* YOU ARE (depressed|sad) .*/I AM SORRY TO HEAR YOU ARE \1/ s/.* YOU ARE (depressed|sad) .*/WHY DO YOU THINK YOU ARE \1/ s/.* all .*/IN WHAT WAY/ s/.* always .*/CAN YOU THINK OF A SPECIFIC EXAMPLE/

Finite-state automata

• Finite-state automata (FSA) • Regular languages • Regular expressions

q 0 b

Finite-state automata (machines)

baa!

baaa!

baaaa!

baaaaa!

...

a a baa+!

a !

q 1 q 2 q 3 state transition q 4 final state

Input tape

q 0

a b a !

Finite-state automata

• • Q: a finite set of N states q 0 , q 1 , … q N  : a finite input alphabet of symbols • • q 0 : the start state • F: the set of final states  (q,i): transition function

State-transition tables

Stat e 0 1 2 3 4 b 1 0 0 0 0 Input a 0 2 3 3 0 !

0 0 0 4 0

Morphemes

• Stems, affixes • Affixes: prefixes, suffixes, infixes: hingi (borrow) – humingi (agent) in Tagalog, circumfixes: sagen – gesagt in German • Concatenative morphology • Templatic morphology (Semitic languages) : lmd (learn), lamad (he studied), limed (he taught), lumad (he was taught)

Morphological analysis

• rewrites • unbelievably

Inflectional morphology

• Tense, number, person, mood, aspect • Five verb forms in English • 40+ forms in French • Six cases in Russian, seven in Polish • Up to 40,000 forms in Turkish (you will cause X to cause Y to … do Z)

Derivational morphology

• Nominalization: computerization, appointee, killer, fuzziness • Formation of adjectives: computational, embraceable, clueless

Finite-state morphological parsing

• Cats: cat +N +PL • Cat: cat +N +SG • Cities: city +N +PL • Geese: goose +N +PL • Ducks: (duck +N +PL) or (duck +V +3SG) • Merging: +V +PRES-PART • Caught: (catch +V +PAST-PART) or (catch +V +PAST)

• IPA • Arpabet • Examples

Phonetic symbols

Using WFST for language modeling

• Phonetic representation • Part-of-speech tagging

Dependency grammars

• Lexical dependencies between head words • Top-level predicate of a sentence is the root • Useful for free word order languages • Also simpler to parse

Dependencies

S VP NP NP NNP VBS JJ NNS John likes tabby cats

Discourse, dialogue, anaphora

• Example:

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

• Example:

I’d like to get from Boston to San Francisco, on either December 5th or December 6th. It’s okay if it stops in another city along the way.

Information extraction and discourse analysis

• Example:

First Union Corp. is continuing to wrestle with severe problems unleashed by a botched merger and a troubled business strategy. According to industry insiders at Paine Webber, their president, John R. Georgius, is planning to retire by the end of the year.

• Problems with summarization and generation

Reference resolution

• The process of reference (associating “John” with “he”).

• Referring expressions and referents.

• Needed: discourse models • Problem: many types of reference!

Example (from Webber 91)

• •

According to John, Bob bought Sue an Integra, and Sue bough Fred a legend.

• But

that

turned out to be a lie. - referent is a speech act.

• • • But

that

was false. - proposition

That

struck me as a funny way to describe the situation. - manner of description

That

caused Sue to become rather poor. - event

That

caused them both to become rather poor. combination of several events.

Reference phenomena

• • Indefinite noun phrases:

I saw an Acura Integra today.

• Definite noun phrases:

The Integra was white.

• Pronouns:

It was white.

• Demonstratives:

this Acura.

• Inferrables:

I almost bought an Acura Integra today, but a door had a dent and the engine seemed noisy.

Mix the flour, butter, and water. Kneed the dough until smooth and shiny.

Constraints on coreference

• Number agreement:

John has an Acura. It is red.

• Person and case agreement:

(*) John and Mary have Acuras. We love them

(where We=John and Mary) • Gender agreement:

John has an Acura. He/it/she is attractive.

• Syntactic constraints: – John bought himself a new Acura.

– John bought him a new Acura.

– John told Bill to buy him a new Acura.

– John told Bill to buy himself a new Acura – He told Bill to buy John a new Acura.

Preferences in pronoun interpretation

• • Recency:

John has an Integra. Bill has a Legend. Mary likes to drive it.

• Grammatical role:

John went to the Acura dealership with Bill. He bought an Integra.

(?) John and Bill went to the Acura dealership. He bought an Integra.

• Repeated mention:

John needed a car to go to his new job. He decided that he wanted something sporty. Bill went to the Acura dealership with him. He bought an Integra.

Preferences in pronoun interpretation

• Parallelism:

Mary went with Sue to the Acura dealership. Sally went with her to the Mazda dealership.

•

??? Mary went with Sue to the Acura dealership. Sally told her not to buy anything.

• Verb semantics:

John telephoned Bill. He lost his pamphlet on Acuras. John criticized Bill. He lost his pamphlet on Acuras.

Salience weights in Lappin and Leass

Sentence recency Subject emphasis Existential emphasis Accusative emphasis Indirect object and oblique complement emphasis Non-adverbial emphasis Head noun emphasis 100 80 70 50 40 50 80

Lappin and Leass (cont’d)

• Recency: weights are cut in half after each sentence is processed.

• Examples: – An Acura Integra is parked in the lot. (subject) – There is an Acura Integra parked in the lot. (existential predicate nominal) – John parked an Acura Integra in the lot. (object) – John gave Susan an Acura Integra. (indirect object) – In his Acura Integra, John showed Susan his new CD player. (demarcated adverbial PP)

Algorithm

1. Collect the potential referents (up to four sentences back).

2. Remove potential referents that do not agree in number or gender with the pronoun.

3. Remove potential referents that do not pass intrasentential syntactic coreference constraints.

4. Compute the total salience value of the referent by adding any applicable values for role parallelism (+35) or cataphora (-175).

5. Select the referent with the highest salience value. In case of a tie, select the closest referent in terms of string position.

Example

• John saw a beautiful Acura Integra at the dealership last week. He showed it to Bill. He bought it.

Rec Subj t Exis Obj Ind Obj Non Adv Hea d N Total 100 80 50 80 310 John Integra dealershi p 100 100 50 50 50 80 80 280 230

Example (cont’d)

Referent John Integra dealership Phrases {John} {a beautiful Acura Integra} {the dealership} Value 155 140 115

Example (cont’d)

Referent John Integra dealership Phrases {John, he 1 } {a beautiful Acura Integra} {the dealership} Value 465 140 115

Example (cont’d)

Referent John Integra dealership Phrases {John, he 1 } {a beautiful Acura Integra, it} {the dealership} Value 465 420 115

Example (cont’d)

Referent John Integra Bill dealership Phrases {John, he 1 } {a beautiful Acura Integra, it} {Bill} {the dealership} Value 465 420 270 115

Example (cont’d)

Referent John Integra Bill dealership Phrases {John, he 1 } {a beautiful Acura Integra, it 1 } {Bill} {the dealership} Value 232.5

210 135 57.5

Observations

• Lappin & Leass - tested on computer manuals 86% accuracy on unseen data.

• Centering (Grosz, Josh, Weinstein): additional concept of a “center” – at any time in discourse, an entity is centered.

• Backwards looking center; forward looking centers (a set).

• Centering has not been automatically tested on actual data.

Part of speech tagging

• Problems: transport, object, discount, address • More problems: content • French: est, président, fils • “Book that flight” – what is the part of speech associated with “book”?

• POS tagging: assigning parts of speech to words in a text.

• Three main techniques: rule-based tagging, stochastic tagging, transformation-based tagging

Rule-based POS tagging

• Use dictionary or FST to find all possible parts of speech • Use disambiguation rules (e.g., ART+V) • Typically hundreds of constraints can be designed manually

Example in French

^ beginning of sentence La rf b nms u article teneur nfs nms noun feminine singular Moyenne jfs nfs v1s v2s v3s adjective feminine singular en p a b preposition uranium nms noun masculine singular des p r preposition rivi`eres nfp noun feminine plural , x punctuation bien_que cs subordinating conjunction délicate jfs adjective feminine singular À p preposition calculer v verb

Sample rules

BS3 BI1

: A BS3 (3rd person subject personal pronoun) cannot be followed by a BI1 (1st person indirect personal pronoun). In the example: `ìl nous faut'' ({\it we need}) - `ìl'' has the tag BS3MS and ``nous'' has the tags [BD1P BI1P BJ1P BR1P BS1P]. The negative constraint ``BS3 BI1'' rules out ``BI1P'', and thus leaves only 4 alternatives for the word ``nous''.

N K

: The tag N (noun) cannot be followed by a tag K (interrogative pronoun); an example in the test corpus would be: ``... fleuve qui ...'' (...river, that...). Since ``qui'' can be tagged both as an `È'' (relative pronoun) and a ``K'' (interrogative pronoun), the `È'' will be chosen by the tagger since an interrogative pronoun cannot follow a noun (``N'').

R V

:A word tagged with R (article) cannot be followed by a word tagged with V (verb): for example ``l' appelle'' (calls him/her). The word `àppelle'' can only be a verb, but ``l''' can be either an article or a personal pronoun. Thus, the rule will eliminate the article tag, giving preference to the pronoun.

Confusion matrix

IN JJ NN IN .2

NNP .2

RB 2.2

VBD VBN JJ .2

8.7

3.3

2.0

.3

2.8

NN 3.3

4.1

.5

.5

NNP RB .7

2.1

1.7

.2

VBD VBN .2

2.6

2.7

.2

4.4

Most confusing: NN vs. NNP vs. JJ, VBD vs. VBN vs. JJ

HMM Tagging

• T = argmax P(T|W), where T=t 1 ,t 2 ,…,t n • By Bayes’s theorem: P(T|W) = P(T)P(W|T)/P(W) • Thus we are attempting to choose the sequence of tags that maximizes the rhs of the equation • P(W) can be ignored • P(T)P(W|T) = ?

• P(T) is called the prior, P(W|T) is called the likelihood.

HMM tagging (cont’d)

• P(T)P(W|T) =  P(w i |w 1 t 1 …w i-1 t i-1 t i )P(t i |t 1 …t i-2 t i-1 ) • Simplification 1: P(W|T) = P(w • Simplification 2: P(T)= i |t i )  P(t i |t i-1 )  i |t i ) P(t i |t i 1 )

Estimates

• P(NN|DT) = C(DT,NN)/C(DT)=56509/116454 = .49

• P(is|VBZ = C(VBZ,is)/C(VBZ)=10073/21627=.47

Example

• Secretariat/NNP is/VBZ expected/VBN to/TO race/VB tomorrow/NR • People/NNS continue/VBP to/TO inquire/VB the/AT reason/NN for/IN the/AT race/NN for/IN outer/JJ space/NN • TO: to+VB (to sleep), to+NN (to school)

Example

NNP VBZ VBN Secretariat is expected TO to NNP VBZ VBN Secretariat is expected TO to

VB

NR race tomorrow

NN

NR race tomorrow

Example (cont’d)

• P(NN|TO) = .00047

• P(VB|TO) = .83

• P(race|NN) = .00057

• P(race|VB) = .00012

• P(NR|VB) = .0027

• P(NR|NN) = .0012

• P(VB|TO)P(NR|VB)P(race|VB) = .00000027

• P(NN|TO)P(NR|NN)P(race|NN) = .00000000032

Decoding

• Finding what sequence of states is the source of a sequence of observations • Viterbi decoding (dynamic programming) – finding the optimal sequence of tags • Input: HMM and sequence of words, output: sequence of states