What is Transliteration?

What is Transliteration?

• What is Transliteration?

• Existing Approaches

• Theory of Syllables

• Phonemes
• What are Syllables?
• Syllable Structure

• Syllabification

• Maximal Onset Principle
• Sonority Hierarchy
• Constraints

• Implementation

• Conclusion & Future Work

• References

Practice of transcribing a word or text written in one writing system into another writing system.

• Practice of transcribing a word or text written in one writing system into another writing system.

• E.g., ‘school’ will be transliterated to ‘skUla’.

• Different from translation:

• ‘school’ will be translated to ‘pazSaalaa’ (‘paathashaala’)

• Why Transliteration?

• Information present in select number of languages.
• Effective knowledge transfer across linguistics require bringing down language barriers.
• Plays an important role in cross-lingual applications.

Given a word (either Hindi or English) written in English language script, we have to:

• Given a word (either Hindi or English) written in English language script, we have to:

• Provide single correct transliterated word in Hindi (Devanagari) script if there is only a single word in Hindi script which could match with the original word.
• Provide two-three most probable options of the transliterated text, in the order of higher to lower probability, if there are more than one words in Hindi script which could match with the original word.

Transliteration methods can be broadly classified into Rule-based and Statistical approaches:

• Transliteration methods can be broadly classified into Rule-based and Statistical approaches:

• Rule-based

• Hand crafted rules are used upon the input source language to generate words of the target language.

• Statistical

• Statistics play a more important role in determining target word generation.

A framework of our approach:

• A framework of our approach:

• A large parallel corpora of names in both English and Hindi languages is taken.
• To prepare the training data, names are syllabified (automatically/manually/both).
• Next, we store the probability with which any Hindi syllable string is mapped to any English syllable string.
• Now, given any new word (test data) written in English language, we use the automatic syllabification of Step 2 to syllabify it.
• Then, we use Viterbi Algorithm to find out three most probable transliterated words with their corresponding probabilities.
• If the probability difference between first and second is too large, we output only the first transliterated word, else all three.
• The study of syllables in any language requires the study of
• phonology of that language.

Phonology

• Phonology

• Study of the structure and systematic patterning of sounds in human language.
• Refers to a description of the sounds of a particular language and the rules governing the distribution of these sounds.

• English Phonology

• No. of speech sounds in English varies from dialect to dialect.
• Longman Dictionary: 24 consonant phonemes (c.p.), 23 vowel phonemes (v.p.), additionally 2 c.p. & 4 v.p. for foreign words.
• American Heritage Dictionary: 25 c.p., 18 v.p., additionally 1 c.p. & 5 v.p. for foreign words.

25 consonant phonemes found in most dialects of English.

• 25 consonant phonemes found in most dialects of English.

• Categorized under six different categories (on the basis of their sonority level, stress, way of pronunciation etc.):

• Nasal: Acoustically, nasal stops are sonorants, meaning they do not restrict the escape of air and cross-linguistically are nearly always voiced.
• Plosive: Produced by stopping the airflow in the vocal tract (the cavity where sound is filtered).
• Affricate: Affricate consonants begin as stops (such as /t/ or /d/) but release as a fricative (such as /s/ or /z/) rather than directly into the following vowel.

Fricative: Produced by forcing air through a narrow channel made by placing two articulators close together. These are the lower lip against the upper teeth in the case of /f/.

• Fricative: Produced by forcing air through a narrow channel made by placing two articulators close together. These are the lower lip against the upper teeth in the case of /f/.

• Approximant: In the articulation of approximants, articulatory organs produce a narrowing of the vocal tract, but leave enough space for air to flow without much audible turbulence. Examples: /l/, as in ‘lip’, and approximants like /j/ and /w/ in ‘yes’ and ‘well’ which correspond closely to vowels.

• Lateral: Laterals are “L”-like consonants pronounced with an occlusion made somewhere along the axis of the tongue, while air from the lungs escapes at one side or both sides of the tongue.

20 vowel phonemes found in most dialects of English.

• 20 vowel phonemes found in most dialects of English.

• Categorized under different categories (on the basis of their sonority level).

Monophthong: “monophthongos” ≡ single note. “pure” vowel sound.

• Monophthong: “monophthongos” ≡ single note. “pure” vowel sound.

• Articulation at both beginning and end is relatively fixed.
• Does not glide up or down towards a new position of articulation.
• Categorized in Short and Long vowels.
• Short: Perceived for a shorter duration. For e.g., /ə/, /e/ etc.
• Long: Comparatively longer duration. For e.g., /i:/, /u:/ etc.

• Diphthong: “two tones”. Vowel combination involving quick but smooth movement from one vowel to another.

• Often interpreted by listeners as a single vowel sound.
• Two target tongue positions.
• Represented by two symbols. For e.g., /eə/

‘Something which syllable has three of’.

• ‘Something which syllable has three of’.

• Stetson’s motor theory:

Count of no. of syllables in a word is roughly/intuitively the no. of vocalic segments in a word.

• 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.

‘word’

• ‘word’

• ‘sprint’

‘may’

• ‘may’

• ‘opt’

• ‘air’

Light Syllable: A syllable which is open and ends in a short vowel.

• Light Syllable: A syllable which is open and ends in a short vowel.

• General Description – CV.
• Example, ‘air’.

• Closed Heavy Syllable: All closed syllables are heavy syllables.

• Example, ‘opt’.

• Closed Heavy Syllable: An open syllable with a nucleus which is long or diphthong is also a heavy syllable.

• Example, ‘may’.

Given a string of syllables (word), what is the coda of one and the onset of another?

• 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

The consonants that form a word-internal onset are the maximal sequence that can be found at the beginning of words.

• The consonants that form a word-internal onset are the maximal sequence that can be found at the beginning of words.

• English permits only 3 consonants to form an onset.

• Once 2nd and 3rd consonants are determined, only 1 consonant can appear in the 1st position.
• Second = /p/, Third = /r/. Then First can only be /s/. E.g., ‘spring’.

• Working: ‘constructs’

• Consonant sequence: n-s-t-r
• Either ‘con structs’ OR ‘cons tructs’ OR ‘const ructs’ OR ‘constr ucts’.
• As, ‘str’ can serve as the onset of a syllable, that’s why the correct syllabification will be ‘con structs’.

Sonority: A perceptual property referring to the loudness of a sound relative to that of other sounds with the same length.

• Sonority: A perceptual property referring to the loudness of a sound relative to that of other sounds with the same length.

• Sonority Hierarchy: Ranking of speech sounds (or phonemes) by amplitude.

• For e.g., if you say the vowel /e/, you will produce louder sound than if you say the plosive /t/.
• It suggests that nuclei are the peaks of sonority and segments on either side of the peak show a decrease in sonority w.r.t. peak.

• Plosives  Affricates  Fricatives  Nasals  Laterals  Approximants  Vowels (Increasing order of sonority).

Phonotactics

• Phonotactics

• Determines possible comb. of onsets and codas which can occur.
• Deals with restriction on the permissible comb. Of phonemes.
• Defines permissible syllable structure, consonant clusters and vowel sequence by means of phonotactical constraints.

• In general, rules operate around the sonority hierarchy.

• Fricative /s/ is lower on the sonority hierarchy than the lateral /l/, so the combination /sl/ is permitted in onsets and /ls/ is permitted in codas. Opposite is not allowed.

• Thus, ‘slips’ and ‘pulse’ are possible English words.

• ‘lsips’ and ‘pusl’ are not possible.

One-consonant: Only /ŋ/ can’t be distributed in syllable-initial position.

• One-consonant: Only /ŋ/ can’t be distributed in syllable-initial position.

• Two-consonant: We refer to the scale of sonority.

• Sequence ‘rn’ is ruled out since there is a decrease of sonority.
• Minimal Sonority Distance: Distance in sonority between the first and the second element in the onset must be of at least 2 degrees.
• Thus, on the basis of Sonority Hierarchy and Minimal Sonority Distance, only a limited no. of possible two-consonant clusters.

• Three-consonant:

• Restricted to licensed two-consonant onsets preceded by /s/.
• Also, /s/ can only be followed by a voiceless sound.
• Therefore, only /spl/, /spr/, /str/, /skr/, /spj/, /stj/, /skj/, /skw/, /skl/, /smj/ will be allowed. (splinter, spray, strong etc.)
• While /sbl/, /sbr/, /sdr/, /sgr/, /sθr/ will be ruled out.

Nucleus: The following can occur as nucleus:

• Nucleus: The following can occur as nucleus:

• All vowel sounds (monophthongs as well as diphthongs).
• /m/, /n/ and /l/ in certain situations (for example, ‘bottom’, ‘apple’)

• Syllabic:

• Both the onset and the coda are optional (as seen previously).
• /j/ at the end of an onset (/pj/, /bj/, /tj/, /dj/, /kj/, /fj/, /vj/, /θj/, /sj/, /zj/, /hj/, /mj/, /nj/, /lj/, /spj/, /stj/, /skj/) must be followed by /uɪ/ or /ʊə/.
• Long vowels and diphthongs are not followed by /ŋ/.
• /ʊ/ is rare in syllable-initial position.
• Stop + /w/ before /uɪ, ʊ, ʌ, aʊ/ are excluded.

Conclusion

• Conclusion

• We took a look at the English to Hindi transliteration problem.
• Explored various techniques used for transliteration between other language pairs.
• Took a look at the approach of syllabification.
• Noticed the results with an accuracy of 99%.

• Future Work

• For the complete goal, following are the things that need to be worked upon:
• We need to syllabify the parallel names in Devanagari script as well.
• System will have to be trained to generate probability of occurrences of English and Hindi syllable pairs.
• This trained system will be used to transliterate any new word provided.

Nasreen AbdulJaleel and Leah S. Larkey. Statistical transliteration for english-arabic cross language information retrieval. In Conference on Information and Knowledge Management, pages 139–146, 2003.

• Nasreen AbdulJaleel and Leah S. Larkey. Statistical transliteration for english-arabic cross language information retrieval. In Conference on Information and Knowledge Management, pages 139–146, 2003.

• Ann K. Farmer Andrian Akmajian, Richard M. Demers and Robert M. Harnish. Linguistics: An Introduction to Language and Communication. MIT Press, 5th edition, 2001.

• Association for Computer Linguistics. Collapsed Consonant and Vowel Models: New Approaches for English-Persian Transliteration and Back-Transliteration, 2007.

• Slaven Bilac and Hozumi Tanaka. Direct combination of spelling and pronunciation information for robust back-transliteration. In Conferences on Computational Linguistics and Intelligent Text Processing, pages 413–424, 2005.

• Ian Lane Bing Zhao, Nguyen Bach and Stephan Vogel. A log-linear block transliteration model based on bi-stream hmms. HLT/NAACL-2007, 2007.

H. L. Jin and K. F. Wong. A Chinese dictionary construction algorithm for information retrieval. In ACM Transactions on Asian Language Information Processing, pages 281–296, December 2002.

• H. L. Jin and K. F. Wong. A Chinese dictionary construction algorithm for information retrieval. In ACM Transactions on Asian Language Information Processing, pages 281–296, December 2002.

• K. Knight and J. Graehl. Machine transliteration. In Computational Linguistics, pages 24(4):599–612, Dec. 1998.

• Lee-Feng Chien Long Jiang, Ming Zhou and Chen Niu. Named entity translation with web mining and transliteration. In International Joint Conference on Artificial Intelligence (IJCAL-07), pages 1629–1634, 2007.

• Dan Mateescu. English Phonetics and Phonological Theory. 2003.

• Della Pietra P. Brown and R. Mercer. The mathematics of statistical machine translation: Parameter estimation. In Computational Linguistics, page 19(2):263U˝ 311, 1990.

• Ganapathiraju Madhavi Prahallad Lavanya and Prahallad Kishore. A simple approach for building transliteration editors for Indian languages. Zhejiang University SCIENCE-2005, 2005.