Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011
description
Transcript of Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011
![Page 1: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/1.jpg)
CS460/626 : Natural Language Processing/Speech, NLP and the Web
(Lecture 35– Phonetics and phonology; syllabification)
Pushpak BhattacharyyaCSE Dept., IIT Bombay
7th April, 2011
![Page 2: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/2.jpg)
Task of converting a word from one alphabetic script to another
Used for: Named entities : Gandhiji Out of vocabulary words : Bank
Motivation for Phonetics and Phonology: Transliteration
![Page 3: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/3.jpg)
Accents: Thoda or thora?
Mapping of sounds Mahaan: Kahaan:
Back-transliteration
Linguistic issues
![Page 4: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/4.jpg)
xTransliteration process
Source String
TransliterationUnits
Target String
TransliterationUnits
![Page 5: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/5.jpg)
Source String
TransliterationUnits
Target String
TransliterationUnits
Phoneme- based
![Page 6: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/6.jpg)
Phoneme-based approach
Word inSource language
Pronunciationin
Source language
Word inTarget language
PronunciationIn
target language
P( ps | ws)
P ( pt | ps )
P ( wt | pt )
Note: Phoneme is the smallest linguistically distinctive unit of sound.
P(wt)
Wt* = argmax (P (wt). P (wt | pt) . P (pt | ps) . P (ps | ws) )
![Page 7: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/7.jpg)
How phonemes play a role
Step I : Consider each character of the word
Transliterating ‘BAPAT’B A P A T
P /ə/ /a://ə/ /a:/B T
Source word to phonemes
P /ə/ /a://ə/ /a:/B T
Source phonemesto target phonemes
t
t
Step II : Converting to phoneme seq.Step III : Converting to target phoneme seq.
![Page 8: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/8.jpg)
Unknown pronunciations
Back-transliteration can be a problem Johnson Jonson
Issues in phonetic model
sanhita
samhita
![Page 9: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/9.jpg)
Back to Phonetics
![Page 10: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/10.jpg)
Ancient 5 x 5 Indian Classification of ConsonantsGroupक वर्ग� क ख र्ग घ ङ Velarच वर्ग� च छ ज झ ञ Palatalट वर्ग� ट ठ ड ढ ण Alveolarत वर्ग� त थ द ध न Dentalप वर्ग� प फ ब भ म Labial
![Page 11: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/11.jpg)
Place of Articulation Labial: Two lips coming together
[p] as in possum, [b] as in bear Dental: Tongue against the teeth
[th] of thing or the [dh] of though Alveolar: Alveolar ridge is the portion of the roof of the mouth just behind the
upper teeth; tip of the tongue against the alveolar ridge. Phones [s], [z], [t], and [d]
Palatal: Roof of the mouth; blade of the tongue against this rising back of the alveolar ridge sounds [sh] (shrimp), [ch] (china), [zh] (Asian), and [jh] (jar)
Velar: Movable muscular flap at the back of the roof of the mouth; back of the tongue up against the velum
sounds [k] (cuckoo), [g] (goose), and [N] (kingfisher) Glottal: closing the glottis (by bringing the vocal folds together)
glottal stop [q] (IPA [P]) is made by closing the glotis
![Page 12: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/12.jpg)
Manner of Articulation: Stops and Nasals
All consonants are produced by restriction of airflow Manner of Articulation; how the restriction is produced:
complete or partial stoppage A stop is a consonant in which airflow is completely blocked for a short
time English has voiced stops like [b], [d], and [g] as well as unvoiced stops like [p],
[t], and [k]. Stops are also called plosives Nasal sounds [n], [m], and [ng] are made by lowering the velum and
allowing air to pass into the nasal cavity
![Page 13: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/13.jpg)
Fricatives Fricatives, airflow is constricted but not cut off completely. The turbulent airflow
that results from the constriction produces a characteristic “hissing” sound. The English labiodental fricatives [f] and [v] are produced by pressing the
lower lip against the upper teeth, allowing a restricted airflow between the upper teeth.
The dental fricatives [th] and [dh] allow air to flow around the tongue between the teeth.
The alveolar fricatives [s] and [z] are produced with the tongue against the alveolar ridge, forcing air over the edge of the teeth.
In the palato-alveolar fricatives [sh] and [zh] the tongue is at the back of the alveolar ridge forcing air through a groove formed in the tongue.
![Page 14: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/14.jpg)
Affricates, Laterals/Liquids and Taps/Flaps
Affricates are stops followed immediately by fricatives English [ch] (chicken); Marathi chaa (e.g., gharaachaa; of the house)
Lateral or Liquids: tip of the tongue up against the alveolar ridge or the teeth, with one or both sides of the tongue lowered to allow air to flow over it
[l] (learn) Tap or flap: quick motion of the tongue against the alveolar ridge
[dx] (IPA [R]) The consonant in the middle of the word lotus ([l ow dx ax s]) is a tap in most
dialects of American English speakers of many UK dialects would use a [t] instead of a tap in this word.
![Page 15: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/15.jpg)
Articulation of consonants: Larynx action/glottis state (1/2)
Vocal cords are pulled apart. The air passes freely through the glottis. This is called the voicelessness state and sounds produced with this configuration of the vocal cords are called voiceless: p t k f θ s ʃ tʃ
Vocal cords are pulled close together. The air passing through the glottis causes the vocal cords to
vibrate. This is called the voicing state and sounds produced with this configuration of the vocal cords are called voiced: b d g v ð z ʒ dʒ
![Page 16: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/16.jpg)
Articulation of consonants: Larynx action/glottis state (2/2)
Vocal cords are apart at the back and pulled together at the front. This is called the whisper state.
Vocal cords assume the voicing state but are relaxed. This is called the murmur state.
![Page 17: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/17.jpg)
Vowels (1/2)
![Page 18: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/18.jpg)
Vowels (2/2)
![Page 19: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/19.jpg)
IPA symbol for Vowels
Courtesy: http://www.antimoon.com/misc/phonchart2008.pdf
![Page 20: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/20.jpg)
IPA symbol for consonants
Courtesy: http://www.antimoon.com/misc/phonchart2008.pdf
![Page 21: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/21.jpg)
Vowels and Tongue Positions
![Page 22: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/22.jpg)
Phonology: Syllables
![Page 23: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/23.jpg)
Basic of syllables“Syllable is a unit of spoken language consisting of a single uninterrupted sound formed generally by a Vowel and preceded or followed by one or more consonants.”
Vowels are the heart of a syllable (Most Sonorous Element) (svayam raajate iti svaraH)
Consonants act as sounds attached to vowels.
![Page 24: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/24.jpg)
Syllable structure A syllable consists of 3 major parts:-
Onset (C) Nucleus (V) Coda (C)
Vowels sit in the Nucleus of a syllable Consonants may get attached as
Onset or Coda. Basic structure - CV
![Page 25: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/25.jpg)
Possible syllable structures The Nucleus is
always present Onset and Coda
may be absent Possible
structures V CV VC CVC
![Page 26: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/26.jpg)
syllable theories Prominence Theory
E.g. entertaining /entəteɪnɪŋ/ The peaks of prominence: vowels /e
ə eɪ ɪ/ Number of syllables: 4
Chest Pulse Theory Based on muscular activities
Sonority Theory Based on relative soundness of
segment within words
![Page 27: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/27.jpg)
Introduction to sonority theory“The Sonority of a sound is its loudness
relative to other sounds with the same length, stress and speech.”
Some sounds are more sonorous Words in a language can be divided into
syllables Sonority theory distinguishes syllables on
the basis of sounds.
![Page 28: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/28.jpg)
Sonority hierarchy Defined on the basis of amount of
sound associated The sonority hierarchy is as follows:-
Vowels (a, e, i, o, u) Liquids (y, r, l, v) Nasals (n, m) Fricatives (s, z, f,…..sh, th etc.) Affricates (ch, j) Stops (b, d, g, p, t, k)
![Page 29: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/29.jpg)
Sonority scale Obstruents can
be further classified into:- Fricatives Affricates Stops
![Page 30: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/30.jpg)
Sonority theory & syllables“A Syllable is a cluster of sonority, defined by a sonority peak acting as a structural magnet to the surrounding lower sonority elements.”
Represented as waves of sonority or Sonority Profile of that syllable Nucleus
Onset Coda
![Page 31: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/31.jpg)
Sonority sequencing principle
“The Sonority Profile of a syllable must rise until its Peak(Nucleus), and then fall.”
Peak (Nucleus)
Onset Coda
![Page 32: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/32.jpg)
examples ABHIJEET
A
BHI
JEET
ABHIJEET
Profile-1
Profile-2
![Page 33: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/33.jpg)
Maximal onset principle“The Intervocalic consonants are maximally
assigned to the Onsets of syllables in conformity with Universal and Language-Specific Conditions.”
Determines underlying syllable division
Example DIPLOMA
DIP LO MA & DI PLO MA
![Page 34: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/34.jpg)
Syllable Structure: a more detailed look
Count of no. of syllables in a word is roughly/intuitively the no. of vocalic segments in a word.
Thus, presence of a vowel is an obligatory element in the structure of a syllable. This vowel is called “nucleus”.
Basic Configuration: (C)V(C). Part of syllable preceding the nucleus is called the
onset. Elements coming after the nucleus are called the
coda. Nucleus and coda together are referred to as the
rhyme.
S ≡ Syllable, O ≡ OnsetR ≡ Rhyme, N ≡ NucleusCo ≡ Coda
![Page 35: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/35.jpg)
Syllable Structure: Examples
‘word’
‘sprint’
![Page 36: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/36.jpg)
Syllable Structure: Examples
‘may’
‘opt’
‘air’
No Coda.
No Onset.
No Coda, No Onset.
![Page 37: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/37.jpg)
Syllable Structure Open Syllable: ends in vowel Closed syllable: ends in consonant or consonant
cluster
Light Syllable: A syllable which is open and ends in a short vowel
General Description – CV. Example, ‘air’.
Heavy Syllable: Closed syllables or syllables ending in diphthong
Example: ‘opt’ Example, ‘may’
![Page 38: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/38.jpg)
Syllabification: Determining Syllable Boundaries
Given a string of syllables (word), what is the coda of one and the onset of another?
In a sequence such as VCV, where V is any vowel and C is any consonant, is the medial C the coda of the first syllable (VC.V) or the onset of the second syllable (V.CV)?
To determine the correct groupings, there are some rules, two of them being the most important and significant:
Maximal Onset Principle, Sonority Hierarchy
![Page 39: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/39.jpg)
Discussion on the assignment
![Page 40: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/40.jpg)
Data The Carnegie Mellon University
Pronouncing Dictionary machine-readable pronunciation
dictionary for North American English that contains over 125,000 words and their transcriptions.
The current phoneme set contains 39 phonemes
![Page 41: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/41.jpg)
“Parallel” CorpusPhoneme Example Translation ------- ------- ----------- AA odd AA D AE at AE T AH hut HH AH T AO ought AO T AW cow K AW AY hide HH AY D B be B IY
![Page 42: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/42.jpg)
“Parallel” Corpus cntdPhoneme Example Translation ------- ------- ----------- CH cheese CH IY Z D dee D IY DH thee DH IY EH Ed EH D ER hurt HH ER T EY ate EY T F fee F IY G green G R IY N HH he HH IY IH it IH T IY eat IY T JH gee JH IY
![Page 43: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/43.jpg)
The tasks First obtain the Carnegie
Mellon University's Pronouncing Dictionary
Train and Test the following Statistical Machine Learning Algorithms
HMM - For HMM you can use either Natural Language Toolkit or you can use GIZA++ with MOSES.
![Page 44: Pushpak Bhattacharyya CSE Dept., IIT Bombay 7 th April, 2011](https://reader036.fdocuments.in/reader036/viewer/2022062315/56816353550346895dd3f490/html5/thumbnails/44.jpg)
Tasks (cntd) Report all the results using 5-
fold cross Validation Compare all the results
obtained in the previous steps in terms of Precision Recall F-Score
Finally do a detailed error analysis.