Latent Class Transliteration based on Source Language Origin
1 like4,309 views
The document presents the latent class transliteration model, which addresses phonetic translations between languages with different writing systems, and proposes modeling source language origins as latent classes. It focuses on improving the transliteration of foreign proper nouns and compares the proposed method to existing models, showing enhanced performance. The research highlights issues with traditional models and suggests future work in broader language applications.
![12
Error Analysis
Example SOFT/HARD LATENT (Proposed)
Felix/フェリックス
ferikkusu [en]
☓ フィリス firisu ✓
Read/リード
riido [en]
☓ レアード reādo ✓
Caen/カーン
kān [fr]
☓ シャーン shān ✓
Laemmle/レムリ
remuri [en]
☓リアム riamu ✓
Xavier/ザビア
zabia [en]
☓ガブリエル
gaburieru
✓
Hilda/イルダ
iruda [en]
☓ ハルラ
harura
☓ ハルラ
harura](https://image.slidesharecdn.com/racl-hlt2011hagiwara-150113222815-conversion-gate01/85/Latent-Class-Transliteration-based-on-Source-Language-Origin-12-320.jpg)
Latent Class Transliteration based on Source Language Origin
- 1. Latent Class Transliteration based on Source Language Origin Masato Hagiwara & Satoshi Sekine Rakuten Institute of Technology, New York ACL-HLT 2011, June 21
- 2. 2 Objective • Transliteration – Phonetic translation between languages with different writing systems e.g., flextime / フレックスタイム furekkusutaimu – Useful for machine translation, spelling variation etc. • Transliteration models – Phonetic-based re-writing models (Knight and Jonathan 1998) – Spelling-based supervised models (Brill and Moore 2000)
- 3. 3 Spelling-based model (Brill and Moore 2000) Edit distance substitution, insertion, deletion = cost 1 Alpha-Beta Model flextime furekkusutaimu Generalization of edit distance string-to-string substitution α→β flextime furekkusutaimu P(flextime→furekkusutaimu) = P(^f→fu)*P(le→re)*P(x→kkusu)*P(ti→tai)*P(me$→mu) Transliteration Probability Maximum re-writing probability over all possible partitions Substitution Prob. α β
- 4. 4 Multiple Language Origins piaget / ピアジェ piaje target / ターゲット tāgetto Single models cannot deal with multiple origins • Class transliteration Model (Li et al. 2007) – Language detection + switching multiple models P(get→ジェ je) ? P(get→ゲット getto) ? piaget / ピアジェ piaje target / ターゲット tāgetto French origin English origin French model English model
- 5. 5 Issues on Class Transliteration Model • Requires training sets tagged with language origins – Rare especially for proper nouns • Language origins ≠ transliteration models – e.g., spaghetti / スパゲティ supageti Italian origins but can be found in English dictionaries – e.g., Carl Laemmle / カール・レムリ kāru remuri German immigrant but listed as an “American” film producer → An English transliteration model doesn’t work Model source language origins as latent classes
- 6. 6 Latent Class Transliteration Model • Proposing “latent class transliteration model” – Models the “source language origins” as latent classes – “latent classes” correspond to sets of words with similar transliteration characteristics – Trained via the EM algorithm from transliteration pairs Class transliteration model Latent class transliteration model (proposed) Explicit language detection Latent class distribution language gender latent class s: source t: target
- 7. 7 Model Training via the EM Algorithm E step Log likelihood M step
- 8. 8 Iterative Learning via EM Algorithm piaget → piaje target → taagetto … p/i/a/get→p/i/a/je t/ar/get→t/aa/getto … Lx Ly Lz Update M step Σγ*f(get$→je) Training Pairs P(^p→p) P(ar→aa) P(get$→je) P(get$→getto) … Transliteration Model Lx Ly Lz P(^p→p) P(ar→aa) P(get$→je) P(get$→getto) … Transliteration Model Lx Ly Lz p/i/a/get→p/i/a/je t/ar/get→t/aa/getto … Lx Ly Lz E step Transliteration probability Based on αβ model
- 9. 9 Experiments • Estimate correct transliteration for foreign proper nouns – Rank the candidates based on probability Top-10 Mean Reciprocal Rank (MRR) • Datasets – Dataset 1: Western person name list (6,718; de+en+fr) – Dataset 2: Western proper noun from Wikipedia (11,323; +it+es)
- 10. 10 Compared Models • Alpha-beta method (AB) • Class transliteration method (SOFT) • Class transliteration method (HARD) • Latent class transliteration method (LATENT – PROPOSED)
- 11. 11Performance measure: Top-10 mean reciprocal rank (MRR) Results Model Dataset 1 Dataset 2 Alpha-beta method AB 94.8 90.9 Class transliteration method HARD 90.3 89.8 Class transliteration method SOFT 95.7 92.4 Latent class transliteration method LATENT (proposed) 95.8 92.4 Higher performance of LATENT vs SOFT/HARD Performance can be higher depending on the number of latent classes Low class detection precision (77.4%)
- 12. 12 Error Analysis Example SOFT/HARD LATENT (Proposed) Felix/フェリックス ferikkusu [en] ☓ フィリス firisu ✓ Read/リード riido [en] ☓ レアード reādo ✓ Caen/カーン kān [fr] ☓ シャーン shān ✓ Laemmle/レムリ remuri [en] ☓リアム riamu ✓ Xavier/ザビア zabia [en] ☓ガブリエル gaburieru ✓ Hilda/イルダ iruda [en] ☓ ハルラ harura ☓ ハルラ harura
- 13. 13 Conclusion • Proposed the “latent class transliteration model” – Models source language origins as latent classes – Model estimation from transliterated pairs via the EM algorithm – Comparable results v.s. models with explicit language origins • Future works – Sources other than Western languages – Targets other than Japanese