natural language processing what it does what is involved why is it difficult brief history

50
Natural Language Processing what it does what is involved why is it difficult brief history

Upload: blanche-little

Post on 16-Dec-2015

218 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Natural Language Processing what it does what is involved why is it difficult brief history

Natural Language Processing

• what it does• what is involved• why is it difficult• brief history

Page 2: Natural Language Processing what it does what is involved why is it difficult brief history

sentence structured repns of meaning"how old is my help3.doc file?"

Lisp: (query (file-detail 'date "C:/help3.doc"))

"the large cat chased the rat"Logic: (1s1 large(s1) feline(s1))

(1s2 rodent(s2)) chased(s1, s2 )

"the young boy ate a bad apple" CD Graph ...see next page...

Page 3: Natural Language Processing what it does what is involved why is it difficult brief history

CD graph "the young boy ate a bad apple"

Page 4: Natural Language Processing what it does what is involved why is it difficult brief history

what is involved

symbolic computationie: symbols manipulated by symbol processors

search & inference

knowledge representation techniques

Page 5: Natural Language Processing what it does what is involved why is it difficult brief history

prejudice, politics, etc

ambiguity...• syntactic• semantic• pragmatic

why is it difficult

Page 6: Natural Language Processing what it does what is involved why is it difficult brief history

example sentences

• the old man the boats• my car drinks petrol• I saw the Eiffel Tower flying to Paris• he opened the door with the key

he opened the door with the squeaking hinge• the boy kicked the ball under the tree

the boy kicked the wall under the tree• put the bottles in the box on the shelf by the door

Page 7: Natural Language Processing what it does what is involved why is it difficult brief history

1950s Russian English translation1956 Chomsky1960s Pattern matching1970s Parsing & some KnRep1980s Kn & inference1990s big dreams small results2000+ quietly promising

(brief) history of language processing

Page 8: Natural Language Processing what it does what is involved why is it difficult brief history

matching:Sir

Page 9: Natural Language Processing what it does what is involved why is it difficult brief history

matching:Student

Page 10: Natural Language Processing what it does what is involved why is it difficult brief history

matching:Elisa

Page 11: Natural Language Processing what it does what is involved why is it difficult brief history

a modernapproach

inputsentence

syntaxanalysis(parsing)

semanticanalysis

pragmaticanalysis

targetrepresentation

grammar

lexicon

semanticrules

contextualinformation

morphologicalprocessing

Page 12: Natural Language Processing what it does what is involved why is it difficult brief history

step 1- morphological processing

objective: strip words into roots & modifiers

issues• inflection (cat pl cat-s)• derivation (happy adj happiness noun)• compounding (toothpaste)

Page 13: Natural Language Processing what it does what is involved why is it difficult brief history

morphological processing - notes

• all(?) spoken lngs exhibit morphology• easier to handle in written lngs if not iconic• some morphology describes infm beyond syntax

eg: proximity (Tamil, Setswana, etc)casespeaker / listener peer relationship

Page 14: Natural Language Processing what it does what is involved why is it difficult brief history

morphology examples

Noun + Suffix Syntactic case Meaning Chennai-ukku dative: destination To Madras Chennai-ukku-irundu dative: source From Madras Chennai-le containment In Madras Chennai-ai object (formal) Madras Fig. 2.2. Suffix Attachment for Noun Cases (Tamil author's spelling)

Proximity Time Things (inanimate) Near i-ppa (this time: now) i-ndtha (this thing: this) Far a-ppa (that time: then) a-ndtha (that thing: that) Question e-ppa (what time: when) e-ndtha (what thing: which) Fig. 2.3. Proximity Information as Prefix Tags (Tamil)

Proximity Cow Student Near Speaker kgomo e (this cow) mo-ithuti yo (this student) Near Listener kgomo e-o (that cow) mo-ithuti yo-o (that student) Far kgomo e-le (that cow) mo-ithuti yo-le (that student) Fig. 2.4. Proximity by Demostrative Pronoun Inflection (Setswana)

Page 15: Natural Language Processing what it does what is involved why is it difficult brief history

step 2- syntax analysis

objectives: 1 check for correctness2 produce phrase structure

uses• parser a rule-based search engine• grammar context-free production rules• lexicon dictionary of words & their

categories

Page 16: Natural Language Processing what it does what is involved why is it difficult brief history

syntax rules

parts of speechrules of combination

consider• the cat chases the mouse• all large black dogs chase cats

Page 17: Natural Language Processing what it does what is involved why is it difficult brief history

example 1 - using Lkit

(build-lexicon

'((a determiner) (cat noun) (dog noun)

(the determiner) (chased verb)))

(build-grammar

'((s1 (sentence -> noun-phrase verb-phrase))

(np (noun-phrase -> determiner noun))

(vp (verb-phrase -> verb noun-phrase))

))

Page 18: Natural Language Processing what it does what is involved why is it difficult brief history

example 1 - output

(parse 'sentence '(the dog chased a cat))

complete-edge 0 5 s1 sentence (the dog ...) nil

s1 sentence -> (noun-phrase verb-phrase)

Syntax

(sentence

(noun-phrase (determiner the) (noun dog))

(verb-phrase

(verb chased)

(noun-phrase (determiner a) (noun cat))))

Semantics

(sentence)

Page 19: Natural Language Processing what it does what is involved why is it difficult brief history

so what ?

we want meaning

Page 20: Natural Language Processing what it does what is involved why is it difficult brief history

Remember: "the young boy ate a bad apple"

how can semantics be encoded as symbols?the boy / an apple?young/old, happy/sad, good/bad?how can semantics be generated?what can be inferred from semantics?

Page 21: Natural Language Processing what it does what is involved why is it difficult brief history

Reminder: "the young boy ate a bad apple"

Page 22: Natural Language Processing what it does what is involved why is it difficult brief history

symbolic representation of semantics

(actor (root boy) (id boy#732)

(tags animate human male)

(qual (age (val 5) (approx 3)))

(quant specific))

(action (primitve INGEST))

(object (root apple) (id nil)

(tags physob veg fruit food)

(qual (phy-state -4))

(quant non-specific))

Page 23: Natural Language Processing what it does what is involved why is it difficult brief history

semantics in lexicon

a simple example

(build-lexicon

'((a det any )

(cat noun feline )

(chased verb hunts )

(dog noun canine )

(the det specific)

))

Page 24: Natural Language Processing what it does what is involved why is it difficult brief history

semantics in grammar rules

(s1 (sentence -> noun-phrase verb-phrase)

(actor . noun-phrase)

(action . verb-phrase.action)

(object . verb-phrase.object)

)

(np (noun-phrase -> det noun)

(det . noun)

)

(vp (verb-phrase -> verb noun-phrase)

(action . verb)

(object . noun-phrase)

)

Page 25: Natural Language Processing what it does what is involved why is it difficult brief history

semantics - results

(parse 'sentence '(the dog chased a cat))

complete-edge 0 5 s1 sentence (the dog...) nil

s1 sentence -> (noun-phrase verb-phrase)

Syntax

(sentence (noun-phrase (det the) (noun dog))

(verb-phrase (verb chased)

(noun-phrase (det a) (noun cat))))

Semantics

(sentence (actor (specific canine))

(action hunts)

(object (any feline)))

Page 26: Natural Language Processing what it does what is involved why is it difficult brief history

semantics in lexicon - checks 1

(a det (sems . any))

(all det (sems . every))

(cat noun (sems . feline) (num . sing))

(cats noun (sems . feline) (num . plur))

(chase verb (sems . hunts) (num . plur))

(chases verb (sems . hunts) (num . sing))

(dog noun (sems . canine) (num . sing))

(dogs noun (sems . canine) (num . plur))

(the det (sems . specific))

Page 27: Natural Language Processing what it does what is involved why is it difficult brief history

semantics in grammar - checks 1

(s1 (sentence -> noun-phrase verb-phrase)

(actor . noun-phrase.sems)

(action . verb-phrase.action)

(object . verb-phrase.object)

; check number of noun-phrase & verb-phrase

(if (noun-phrase.number

= verb-phrase.number)

numeric-agreement-ok

numeric-agreement-bad

)

)

Page 28: Natural Language Processing what it does what is involved why is it difficult brief history

semantics - results

(parse 'sentence '(the dog chases a cat))

complete-edge 0 5 s1 sentence (the dog...) nil

s1 sentence -> (noun-phrase verb-phrase)

Syntax

(sentence (noun-phrase (det the) (noun dog))

(verb-phrase (verb chases)

(noun-phrase (det a) (noun cat))))

Semantics

(sentence (actor specific canine)

(action . hunts)

(object any feline)

numeric-agreement-ok)

Page 29: Natural Language Processing what it does what is involved why is it difficult brief history

semantics - results

(parse 'sentence '(the dogs chases a cat))

complete-edge 0 5 s1 sentence (the dog...) nil

s1 sentence -> (noun-phrase verb-phrase)

Syntax

(sentence (noun-phrase (det the) (noun dog))

(verb-phrase (verb chases)

(noun-phrase (det a) (noun cat))))

Semantics

(sentence (actor specific canine)

(action . hunts)

(object any feline)

numeric-agreement-bad)

Page 30: Natural Language Processing what it does what is involved why is it difficult brief history

semantics in grammar - checks 2

(s1 (sentence -> noun-phrase verb-phrase)

(fail if noun-phrase.number

/= verb-phrase.number)

(actor . noun-phrase.sems)

(action . verb-phrase.action)

(object . verb-phrase.object)

)

Page 31: Natural Language Processing what it does what is involved why is it difficult brief history

semantics - results

(parse 'sentence '(the dog chases a cat))

Semantics

(sentence (actor specific canine)

(action . hunts)

(object any feline))

(parse 'sentence '(the dogs chases a cat))

.... failed ....

Page 32: Natural Language Processing what it does what is involved why is it difficult brief history

semantics in grammar - checks 3

(s1 (sentence -> noun-phrase verb-phrase)

(glitch numeric-agreement

if not noun-phrase.number

= verb-phrase.number)

(actor . noun-phrase.sems)

(action . verb-phrase.action)

(object . verb-phrase.object)

)

Page 33: Natural Language Processing what it does what is involved why is it difficult brief history

semantics - results

(parse 'sentence '(the dogs chases a cat))

complete-edge 0 5 s1 sentence (the dogs...) nil

Glitches: (numeric-agreement)

s1 sentence -> (noun-phrase verb-phrase)

Syntax

(sentence (noun-phrase (det the) (noun dogs))

(verb-phrase (verb chases)

(noun-phrase (det a) (noun cat))))

Semantics

(sentence (actor specific canine)

(action . hunts)

(object any feline))

Page 34: Natural Language Processing what it does what is involved why is it difficult brief history

example 2 - lexicon

(a det any )

(cat noun feline )

(chase verb hunts )

(dog noun canine )

(the det specific)

(black adj (color black))

(large adj (size 7/10))

(small adj (size 3/10))

Page 35: Natural Language Processing what it does what is involved why is it difficult brief history

example 2 - grammar

(build-grammar

'((np (noun-phrase -> ?det *adj noun)

(if det

(quantification . det)

(quantification undefined))

(qualifiers . *.adj)

(object . noun)

))

))

Page 36: Natural Language Processing what it does what is involved why is it difficult brief history

example 2 - results

(parse 'noun-phrase '(small black dog))

complete-edge 0 3 np noun-phrase (small...) nil

np noun-phrase -> (?det *adj noun)

Syntax

(noun-phrase (adj small) (adj black) (noun dog))

Semantics

(noun-phrase

(quantification undefined)

(qualifiers ((size . 3/10)) ((color . black)))

(object canine))

Page 37: Natural Language Processing what it does what is involved why is it difficult brief history

example 2 - resultssmall dogs chase the small cats

and large dogs chase the large cats

(sentence conjunction

((actor (quant undefined) (qual (size . 3/10))

(object . canine))

(action . hunts)

(object (quant . specific) (qual (size . 3/10))

(object . feline)))

((actor (quant undefined) (qual (size . 7/10))

(object . canine))

(action . hunts)

(object (quant . specific) (qual (size . 7/10))

(object . feline))))

Page 38: Natural Language Processing what it does what is involved why is it difficult brief history

semantic processing (one approach)

• semantic rules in grammar 1st stage case frame• verb form primitive action case frame• disambiguate & fill additional case frame slots• check references with world and/or dialog• do statement level inference• integrate with dialog• do event sequence dialog

Page 39: Natural Language Processing what it does what is involved why is it difficult brief history

step-1: produce raw case frame

• verb casesthe cat chased the rat in the kitchenthe cat chased the rat into the kitchen

• common casessource start-time instrumentdestination end-time beneficiarylocation duration

Page 40: Natural Language Processing what it does what is involved why is it difficult brief history

the ambiguity problem

eg: the boy kicked the ball under the tree

grammar rulesS S PPS NP VPNP ?det *adj nounNP NP PP

Page 41: Natural Language Processing what it does what is involved why is it difficult brief history

example frame #1

actor (quant specific)

(tags animate male human)

(qual (age (range 3 13)))

(root boy)

action (root kick)

object (root ball)

(tags manip)

(posn-relative

(locator beneath)

(object (root tree)

...etc... )

Page 42: Natural Language Processing what it does what is involved why is it difficult brief history

example frame #2

actor (quant specific)

(tags animate male human)

(qual (age (range 3 13)))

(root boy)

action (root kick)

object (root ball)

(tags manip)

dest (posn-relative

(locator beneath)

(object (root tree)

...etc... )

Page 43: Natural Language Processing what it does what is involved why is it difficult brief history

example verb form #1

primitive strike

prohibited object (tags manip)

slots instrument (part-of $actor foot)

legal start-time, end-time, duration

instrument, beneficiary, location

illegal source, dest

Page 44: Natural Language Processing what it does what is involved why is it difficult brief history

example verb form #2

primitive push

required object (tags manip)

slots instrument (part-of $actor foot)

legal source, dest, start-time, end-time,

instr, beneficiary, locatn, duration

Page 45: Natural Language Processing what it does what is involved why is it difficult brief history

semantic processing (one approach)

× semantic rules in grammar 1st stage case frame× verb form primitive action case frame× disambiguate & fill additional case frame slots check references with world and/or dialog do statement level inference• integrate with dialog• do event sequence dialog

Page 46: Natural Language Processing what it does what is involved why is it difficult brief history

integration with dialog

dialogs have...• players (actors)• props (objects)• locations (from case frames)• themes (derived)• event sequences (from themes)• plans (from themes and/or derived)

Page 47: Natural Language Processing what it does what is involved why is it difficult brief history

event sequence

set of...• players (actors)• props (objects)

series of...• semantically encoded activities (matched)• escapes, exceptions & alternatives

Page 48: Natural Language Processing what it does what is involved why is it difficult brief history

reading – grammars, etc

 A good source of links & references...“Computational Analysis of Prepositions” http://knol.google.com/k/abdul-baqi-sharaf/computational-analysis-of-prepositions/3hc3uny2z7r41/4# if you only plan to read one article...Baldwin, T. Kordoni, V and Villavicencio, A. 2009. Prepositions in Applications: A Survey and Introduction to the Special Issue ". Computational Linguistics 35 (2): 119–149. also...

Litkowski, Kenneth C. and Orin Hargraves. 2007. SemEval-2007 task 06: Word-sense disambiguation of prepositions. In Proceedings of the 4th International Workshop on Semantic Evaluations, pages 24–29, Prague. Disambiguation of Preposition Sense Using Linguistically MotivatedFeatures, Stephen Tratz and Dirk Hovy. Proceedings of the NAACL HLT Student Research Workshop and Doctoral Consortium, pages 96–100,Boulder, Colorado, June 2009. c 2009 Association for Computational Linguistics 

Page 49: Natural Language Processing what it does what is involved why is it difficult brief history

reading – grammars, etc

 the NLP dictionary: www.cse.unsw.edu.au/~billw/nlpdict.html for practical help with building grammars check the following (it is about 10 years old but then so is the English language :o)A Grammar Writer’s Cookbook. Miriam Butt, Tracy Holloway King, Marma-Eugenia Niño and Fridirique Segond also (for writing larger grammars) it is useful to find a book on grammar for tutors and/or students of English as a second language.

for a broad (if a little formal) take on semantics try dipping into...Semantics-Oriented Natural Language Processing Mathematical Models and Algorithms. Vladimir Fomichov A. 2010

 

Page 50: Natural Language Processing what it does what is involved why is it difficult brief history

reading – kn rep for NLP

logic and knowledge representation – a guidehttp://dspace.dsto.defence.gov.au/dspace/bitstream/1947/9996/1/DSTO-TR-

2324%20PR.pdf representing events for NLPhttp://www.google.co.uk/url?sa=t&rct=j&q=knowledge%20representation

%20%22representing%20events%22&source=web&cd=6&sqi=2&ved=0CEgQFjAF&url=http%3A%2F%2Fwww.aaai.org%2Focs%2Findex.php%2FFSS%2FFSS10%2Fpaper%2Fdownload%2F2183%2F2819&ei=f6oWT_e7DeKC4gTMpaijBA&usg=AFQjCNFYmurwJR9oqfCRBimVprWRK45kew&cad=rja

 semantic networks & frames (2005)http://www.cs.bham.ac.uk/~jxb/IAI/w6.pdf VERL: An Ontology Framework for Video Events (2005)http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1524892