ProcessingSpeech NLP and the Web Lecture 1 Introduction Pushpak Bhattacharyya CSE Dept IIT Bombay 4 th Jan 2011 Persons involved Faculty instructors Dr Pushpak Bhattacharyya ID: 807277
Download The PPT/PDF document "CS460/626 : Natural Language" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
CS460/626 : Natural Language Processing/Speech, NLP and the Web(Lecture 1 – Introduction)
Pushpak Bhattacharyya
CSE Dept.,
IIT
Bombay
4
th
Jan
,
2011
Persons involvedFaculty instructors: Dr. Pushpak Bhattacharyya (www.cse.iitb.ac.in/~pb)TAs: Joydip Datta,
Debarghya
Majumdar
{
joydip,deb
}@
cse
Course home page (to be created)
www.cse.iitb.ac.in/~
cs626-460-2011
Slide3Perpectivising NLP: Areas of AI and their inter-dependencies
Search
Vision
Planning
Machine Learning
Knowledge Representation
Logic
Expert Systems
Robotics
NLP
Slide4Books etc.Main Text(s):Natural Language Understanding: James Allan
Speech and NLP: Jurafsky and Martin
Foundations of Statistical NLP: Manning and Schutze
Other References:
NLP a Paninian Perspective: Bharati, Cahitanya and Sangal
Statistical NLP: Charniak
Journals
Computational Linguistics, Natural Language Engineering, AI, AI Magazine, IEEE SMC
Conferences
ACL, EACL, COLING, MT Summit, EMNLP, IJCNLP, HLT, ICON, SIGIR, WWW, ICML, ECML
Slide5Allied Disciplines
Philosophy
Semantics, Meaning of “meaning”, Logic (syllogism)
Linguistics
Study of Syntax, Lexicon, Lexical Semantics etc.
Probability and Statistics
Corpus Linguistics, Testing of Hypotheses, System Evaluation
Cognitive Science
Computational Models of Language Processing, Language Acquisition
Psychology
Behavioristic insights into Language Processing, Psychological Models
Brain Science
Language Processing Areas in Brain
Physics
Information Theory, Entropy, Random Fields
Computer Sc. & Engg.
Systems for NLP
Slide6Topics proposed to be coveredShallow ProcessingPart of Speech Tagging and Chunking using HMM, MEMM, CRF, and Rule Based Systems
EM Algorithm
Language Modeling
N-grams
Probabilistic CFGs
Basic
Speech Processing
Phonology and Phonetics
Statistical Approach
Automatic Speech Recognition and Speech Synthesis
Deep ParsingClassical Approaches: Top-Down, Bottom-UP and Hybrid MethodsChart Parsing,
Earley ParsingStatistical Approach: Probabilistic Parsing, Tree Bank Corpora
Slide7Topics proposed to be covered (contd.)Knowledge Representation and NLP
Predicate Calculus, Semantic Net, Frames, Conceptual Dependency, Universal Networking Language (UNL)
Lexical Semantics
Lexicons, Lexical Networks and Ontology
Word Sense Disambiguation
Applications
Machine Translation
IR
Summarization
Question Answering
Slide8GradingBased onMidsemEndsemAssignmentsPaper-reading/Seminar
Except the first two everything else in groups of 4.
Weightages
will be revealed soon.
Slide9Definitions etc.
Slide10What is NLPBranch of AI2 GoalsScience Goal: Understand the way language operatesEngineering Goal: Build systems that analyse and generate language; reduce the man machine gap
Slide11The famous Turing Test: Language Based Interaction
Machine
Human
Test conductor
Can the test conductor find out which is the machine and which
the human
Slide12Inspired Elizahttp://www.manifestation.com/neurotoys/eliza.php3
Slide13Inspired Eliza (another sample interaction)A Sample of Interaction:
Slide14“What is it” question: NLP is concerned with Grounding
Ground the language into perceptual, motor and cognitive capacities.
Slide15Grounding
Chair
Computer
Slide16Two Views of NLP and the Associated ChallengesClassical ViewStatistical/Machine Learning View
Slide17Stages of processingPhonetics and phonologyMorphologyLexical AnalysisSyntactic AnalysisSemantic AnalysisPragmaticsDiscourse
Slide18PhoneticsProcessing of speechChallengesHomophones: bank (finance) vs. bank (river
bank)
Near Homophones:
maatraa
vs.
maatra (hin)
Word Boundaryaajaayenge (aa jaayenge (will come) or aaj aayenge (will come today)I got [ua]plate
Phrase boundarymtech1 students are especially exhorted to attend as such seminars are integral to one's post-graduate educationDisfluency: ah, um, ahem etc.
Slide19MorphologyWord formation rules from root wordsNouns: Plural (boy-boys); Gender marking (czar-czarina)Verbs: Tense (
stretch-stretched);
Aspect (
e.g. perfective sit-had sat
); Modality (e.g.
request khaanaa
khaaiie)First crucial first step in NLPLanguages rich in morphology: e.g., Dravidian, Hungarian, TurkishLanguages poor in morphology: Chinese, EnglishLanguages with rich morphology have the advantage of easier processing at higher stages of processingA task of interest to computer science: Finite State Machines for Word Morphology
Slide20Lexical AnalysisEssentially refers to dictionary access and obtaining the properties of the word e.g. dog noun (lexical property)
take-’s’-in-plural (morph property)
animate (semantic property)
4-legged (-do-)
carnivore (-do)
Challenge:
Lexical or word sense disambiguation
Slide21Lexical DisambiguationFirst step: part of Speech DisambiguationDog as a noun (animal)
Dog
as a verb (
to pursue)
Sense Disambiguation
Dog (
as
animal)Dog (as a very detestable person)Needs word relationships in a context
The chair emphasised the need for adult educationVery common in day to day communicationsSatellite Channel Ad: Watch what you want, when you want (two senses of watch)
e.g., Ground breaking ceremony/research
Slide22Technological developments bring in new terms, additional meanings/nuances for existing termsJustify as in justify the right margin (word processing context)Xeroxed: a new verbDigital Trace:
a new expression
Communifaking:
pretending to talk on mobile when you are actually not
Discomgooglation:
anxiety/discomfort at not being able to access internet
Helicopter Parenting
: over parenting
Slide23Syntax Processing StageStructure Detection
S
NP
VP
V
NP
I
like
mangoes
Slide24Parsing StrategyDriven by grammarS-> NP VPNP-> N | PRONVP-> V NP | V PPN-> MangoesPRON-> IV-> like
Slide25Challenges in Syntactic Processing: Structural AmbiguityScope1.The old men and women were taken to safe locations(old men and women)
vs.
((old men) and women)
2. No smoking areas will allow Hookas inside
Preposition Phrase Attachment
I saw the boy with a telescope
(who has the
telescope?)I saw the mountain with a telescope
(world knowledge: mountain cannot be an instrument of seeing)I saw the boy with the pony-tail
(world knowledge: pony-tail cannot be an instrument of seeing)Very ubiquitous: newspaper headline “20 years later, BMC pays father 20 lakhs for causing son’s death”
Structural Ambiguity…OverheardI did not know my PDA had a phone for 3 monthsAn actual sentence in the newspaperThe camera man shot the man with the gun when he was near Tendulkar
(P.G. Wodehouse,
Ring in Jeeves) Jill had rubbed ointment on Mike the Irish Terrier, taken a look at the goldfish belonging to the cook, which had caused anxiety in the kitchen by refusing its ant’s eggs…
(Times of India, 26/2/08)
Aid for kins of cops killed in terrorist attacks
Slide27Headache for Parsing: Garden Path sentencesGarden PathingThe horse raced past the garden fell.The old man the boat.Twin Bomb Strike in Baghdad kill 25 (Times of India 05/09/07)
Slide28Semantic AnalysisRepresentation in terms ofPredicate calculus/Semantic Nets/Frames/Conceptual Dependencies and ScriptsJohn gave a book to Mary
Give action: Agent: John, Object: Book, Recipient: Mary
Challenge: ambiguity in semantic role labeling
(Eng) Visiting aunts can be a nuisance
(Hin) aapko mujhe mithaai khilaanii padegii (ambiguous in Marathi and Bengali too; not in Dravidian languages)
Slide29PragmaticsVery hard problemModel user intentionTourist (in a hurry, checking out of the hotel, motioning to the service boy): Boy, go upstairs and see if my sandals are under the divan. Do not be late. I just have 15 minutes to catch the train.Boy (running upstairs and coming back panting): yes sir, they are there.
World knowledge
WHY INDIA NEEDS A SECOND OCTOBER (
ToI, 2/10/07)
Slide30DiscourseProcessing of sequence of sentences
Mother
to
John
:
John go to school. It is open today. Should you bunk? Father will be very angry.
Ambiguity of openbunk what?
Why will the father be angry? Complex chain of reasoning and application of world knowledge Ambiguity of
father father as parent
or father as headmaster
Slide31Complexity of Connected Text John was returning from school dejected – today was the math test
He couldn’t control the class
Teacher shouldn’t have made him
responsible
After all he is just a janitor
Slide32A look at Textual HumourTeacher (angrily): did you miss the class yesterday?Student: not much
A man coming back to his parked car sees the sticker "Parking fine". He goes and thanks the policeman for appreciating his parking skill.
Son
: mother, I broke the
neighbour's
lamp shade.
Mother
: then we have to give them a new one.Son: no need, aunty said the lamp shade is irreplaceable.
Ram: I got a Jaguar car for my unemployed youngest son.Shyam: That's a great exchange!
Shane Warne should bowl maiden overs, instead of bowling maidens over
Slide33Giving a flavour of what is done in NLP: Structure Disambiguation
Scope, Clause and Preposition/Postpositon
Slide34Structure Disambiguation is as critical as Sense DisambiguationScope (portion of text in the scope of a modifier)Old men and women will be taken to safe locations
No smoking areas allow hookas inside
Clause
I told the child that I liked that he came to the game on time
Preposition
I saw the boy with a telescope
Slide35Structure Disambiguation is as critical as Sense Disambiguation (contd.)Semantic roleVisiting aunts can be a nuisance
Mujhe
aapko
mithaai
khilaani
padegii (“I have to give you sweets” or “You have to give me sweets”)Postposition
unhone teji se bhaaagte hue chor
ko pakad liyaa (“he caught the thief that was running fast” or “he ran fast and caught the thief”)
All these ambiguities lead to the construction of multiple parse trees for each sentence and need semantic, pragmatic and discourse cues for disambiguation
Slide36Higher level knowledge needed for disambiguationSemanticsI saw the boy with a pony tail (pony tail cannot be an instrument of seeing)
Pragmatics
((old men) and women)
as opposed to
(old men and women)
in “
Old men and women were taken to safe location”
, since women- both and young and old- were very likely taken to safe locationsDiscourse:
No smoking areas allow hookas inside, except the one in Hotel Grand.No smoking areas allow hookas inside, but not cigars.
Slide37Preposition Attachment Disambiguation
Slide38Problem definition4-tuples of the form V N1 P N2
saw (V) boys (N
1
) with (P) telescopes (N
2
)Attachment choice is between the matrix verb V and the object noun N1
Slide39Lexical Association Table (Hindle and Rooth, 1991 and 1993)From a large corpus of parsed textfirst find all noun phrase headsthen record the verb (if any) that precedes the head
and the preposition (if any) that follows it
as well as some other syntactic information about the sentence.
Extract attachment information from this table of co-occurrences
Slide40Example: lexical associationA table entry is considered a definite instance of the prepositional phrase attaching to the verb if:the verb definitely licenses the prepositional phrase
E.g. from Propbank,
absolve
frames
absolve.XX:
NP-ARG0 NP-ARG2-of obj-ARG1
1
absolve.XX NP-ARG0 NP-ARG2-of obj-ARG1 On Friday , the firms filed a suit *ICH*-1 against West Virginia in New York state court asking for [
ARG0 a declaratory judgment] [rel absolving] [ARG1 them] of [ARG2-of liability]
.
Slide41Core stepsSeven different procedures for deciding whether a table entry is an instance of no attachment, sure noun attach, sure verb attach, or ambiguous attachable to extract frequency information, counting the number of times a particular verb or noun attaches with a particular preposition
Slide42Core steps (contd.)These frequencies serve as the training data for the statistical model used to predict correct attachmentTo disambiguate a sentence, compute the likelihood of the particular preposition given the particular verb and contrast with the likelihood of the preposition given the particular noun
i.e., compare
P(with
|
saw)
with
P(with|telescope)
as in I saw the boy with a telescope
Slide43CritiqueLimited by the number of relationships in the training corpora Too large a parameter spaceModel acquired during training is represented in a huge table of probabilities, precluding any straightforward analysis of its workings
Slide44Approach based on Transformation Based Error Driven Learning, Brill and Resnick, COLING 1994
Slide45Example Transformations
Initial attach-
ments by default
are to N1 pre-
dominantly.
Slide46Transformation rules with word classes
Wordnet synsets
and
Semantic classes
used
Slide47Accuracy values of the transformation based approach: 12000 training and 500 test examples
Method
Accuracy
#of transformation rules
Hindle and Rooth
(baseline)
70.4 to 75.8%
NA
Transformations
79.2
418
Transformations
(word classes)
81.8
266
Slide48Maximum Entropy Based Approach: (Ratnaparki, Reyner, Roukos, 1994)Use more features than (V N1) bigram and (N1 P) bigramApply Maximum Entropy Principle
Slide49Core formulationWe denote the partially parsed verb phrase, i.e., the verb phrase without the attachment decision, as a history h, and the conditional probability of an attachment as
P(d
|
h)
,
where
d and corresponds to a noun or verb attachment- 0 or 1- respectively.
Slide50Maximize the training data log likelihood
--(1)
--(2)
Slide51Equating the model expected parameters and training data parameters
--(3)
--(4)
Slide52FeaturesTwo types of binary-valued questions:Questions about the presence of any n-gram of the four head words, e.g., a bigram maybe V == ‘‘is’’, P == ‘‘of’’Features comprised solely of questions on words are denoted as “word” features
Slide53Features (contd.)Questions that involve the class membership of a head wordBinary hierarchy of classes derived by mutual information
Slide54Features (contd.)Given a binary class hierarchy, we can associate a bit string with every word in the vocabulary
Then, by querying the value of certain bit positions we can construct
binary questions.
Features comprised solely of questions about class bits are denoted as “class” features, and features containing questions about both class bits and words are denoted as “mixed” features.
Slide55Word classes (Brown et. al. 1992)
Slide56Experimental data size
Slide57Performance of ME Model on Test Events
Slide58Examples of Features Chosen for Wall St. Journal Data
Slide59Average Performance of Human & ME Model on300 Events of WSJ Data
Slide60Human and ME model performance on consensus set for WSJ
Slide61Average Performance of Human & ME Model on200 Events of Computer Manuals Data
Slide62Back-off model based approach (Collins and Brooks, 1995) NP-attach: (joined ((the board) (as a non executive director)))
VP-attach:
((joined (the board)) (as a non executive director))
Correspondingly,
NP-attach:
1 joined board as director
VP-attach:
0 joined board as director
Quintuple of (attachment: A: 0/1, V, N1, P, N2)5 random variables
Slide63Probabilistic formulation
Or briefly,
If
Then the attachment is to the noun, else to the verb
Slide64Maximum Likelihood estimate
Slide65The Back-off estimate
Inspired by speech recognition
Prediction of the
N
th
word from previous (N-1) words
Data sparsity problem
f(w
1
, w
2
, w3,…w
n) will frequently be 0 for large values on n
Slide66Back-off estimate contd.
The cut off frequencies (c
1
, c
2
....) are thresholds determining whether to back-off or not at each level-
counts lower than
ci at stage i are deemed
to be too low to give an accurate estimate, so in this case
backing-off continues.
Slide67Back off for PPT attachment
Note: the back off tuples always retain the preposition
Slide68The backoff algorithm
Slide69Lower and upper bounds on performance
Lower bound
(most frequent)
Upper bound
(human experts
Looking at 4 word
only)
Slide70Results
Slide71Comparison with other systems
Maxent,
Ratnaparkhi et. al.
Transformation
Learning,
Brill et. al.
Slide72Flexible Unsupervised PP Attachment using WSD and Data Sparsity Reduction: (Medimi Srinivas and Pushpak Bhattacharyya, IJCAI 2007)Unsupervised approach (some way similar to Ratnaparkhi 1998): The training data is extracted from raw text
The unambiguous training data of the form V-P-N and N1-P-N2 TEACH the system how to resolve PP-attachment in ambiguous test data V-N1-P-N2
Refinement of extracted training data. And use of N2 in PP-attachment resolution process.
Slide73Flexible Unsupervised PP Attachment using WSD and Data Sparsity Reduction: (Medimi Srinivas and Pushpak Bhattacharyya, IJCAI 2007)PP-attachment is determined by the semantic property of lexical items in the context of preposition using WordNet
An Iterative Graph based unsupervised approach is used for Word Sense disambiguation (Similar to Mihalcea 2005)
Use of a Data sparseness Reduction (DSR) Process which uses lemmatization, Synset replacement and a form of inferencing. DSRP uses WordNet.
Flexible use of WSD and DSR processes for PP-Attachment
Slide74Graph based disambiguation: page rank based algorithm,
Mihalcea 2005
Slide75Experimental setupTraining Data: Brown corpus (raw text). Corpus size is 6 MB, consists of 51763 sentences, nearly 1 million 27 thousand words.
Most frequent Prepositions in the syntactic context N1-P-N2:
of, in, for, to, with, on, at, from, by
Most frequent Prepositions in the syntactic context V-P-N:
in, to, by, with, on, for, from, at, of
The Extracted unambiguous N1-P-N2: 54030 and V-P-N: 22362
Test Data:
Penn Treebank Wall Street Journal (WSJ) data extracted by RatnaparkhiIt consists of V-N1-P-N2
tuples: 20801(training), 4039(development) and 3097(Test)
Slide76Experimental setup contd.BaseLine: The unsupervised approach by Ratnaparkhi, 1998 (
Base-RP
).
Preprocessing
:
Upper case to lower case
Any four digit number less than 2100 as a year
Any other number or % signs are converted to
numExperiments are performed using DSRP: with different stages of DSRP Experiments are performed using GuWSD and DSRP: with different senses
Slide77The process of extracting training data: Data Sparsity Reduction
Tools/process
Output
Raw Text
The professional conduct of the doctors is guided by Indian Medical Association.
POS Tagger
The_DT professional_JJ conduct_NN of_IN the_DT doctors_NNS is_VBZ guided_VBN by_ IN Indian_NNP Medical_NNP Association_NNP._.
Chunke
r
[The_DT professional_JJ conduct_NN ] of_IN [the_DT doctors_NNS ] (is_VBZ guided_VBN) by_IN [Indian_NNP Medical_NNP Association_NNP].
After replacing each chunk by its head word it results in:
conduct_NN of_IN doctors_NNS guided_VBN by_IN Association_NNP
Extraction Heuristics
N
1
PN
2
: conduct of doctors and
VPN
: guided by Association
Morphing
N
1
PN
2
: conduct of doctor and
VPN
: guide by association
DSRP (Synset Replacement)
N
1
PN
2
: {conduct, behavior} of {doctor, physician} can result in 4 combination with the same sense and similarly for
VPN
: {guide, direct} by {association} can result in 2 combinations with the same sense.
Slide78Data Sparsity Reduction: Inferencing If V1-P-N
1
and V
2
-P-N
1
exist as also do V1
-P- N2 and V2-P-N2, then if
V3-P-Ni exist (i=1,2), then we can infer the existence of V3-P-N
J (i ≠ j) with a frequency count of V3-P-Ni that can be added to the corpus.
Slide79Example of DSR by inferencingV1-P-N1: play in garden and V2-P-N1
:
sit in garden
V
1
-P-N2:
play in house and V2-P-N2: sit in houseV3-P-N2:
jump in house existsInfer the existence of V3-P-N1: jump in garden
Slide80Results
Slide81Effect of various processes on FlexPPAttach algorithm
Slide82Precision vs. various processes