Vanda A Statistical Machine Translation Toolkit Matthias B uchse - PowerPoint PPT Presentation

Vanda A Statistical Machine Translation Toolkit Matthias B¨ uchse Toni Dietze Johannes Osterholzer Anja Fischer Linda Leuschner WATA, Dresden, 2012-05-30 1 / 15

Outline State of the Art Vanda: Aims and Solutions 2 / 15

Outline State of the Art Vanda: Aims and Solutions 3 / 15

Machine Translation . . . . . . ich s¨ age ihre ente i saw her duck ich sah, wie sie sich duckte i saw her ducking ich esse spaghetti mit der gabel i eat spaghetti with a fork ich esse spaghetti mit fleischkl¨ oßen i eat spaghetti with meatballs . . . . . . F E 4 / 15

Machine Translation . . . . . . ich s¨ age ihre ente i saw her duck ich sah, wie sie sich duckte i saw her ducking ich esse spaghetti mit der gabel i eat spaghetti with a fork ich esse spaghetti mit fleischkl¨ oßen i eat spaghetti with meatballs . . . . . . h F E 4 / 15

Machine Translation . . . . . . ich s¨ age ihre ente i saw her duck ich sah, wie sie sich duckte i saw her ducking ich esse spaghetti mit der gabel i eat spaghetti with a fork ich esse spaghetti mit fleischkl¨ oßen i eat spaghetti with meatballs . . . . . . h F E modelling select H ⊆ E F 4 / 15

Machine Translation . . . . . . ich s¨ age ihre ente i saw her duck ich sah, wie sie sich duckte i saw her ducking ich esse spaghetti mit der gabel i eat spaghetti with a fork ich esse spaghetti mit fleischkl¨ oßen i eat spaghetti with meatballs . . . . . . h F E modelling select H ⊆ E F decoding apply any given h ∈ H 4 / 15

Machine Translation . . . . . . ich s¨ age ihre ente i saw her duck ich sah, wie sie sich duckte i saw her ducking ich esse spaghetti mit der gabel i eat spaghetti with a fork ich esse spaghetti mit fleischkl¨ oßen i eat spaghetti with meatballs . . . . . . h F E modelling select H ⊆ E F decoding apply any given h ∈ H training select h ∈ H 4 / 15

Machine Translation . . . . . . ich s¨ age ihre ente i saw her duck ich sah, wie sie sich duckte i saw her ducking ich esse spaghetti mit der gabel i eat spaghetti with a fork ich esse spaghetti mit fleischkl¨ oßen i eat spaghetti with meatballs . . . . . . h F E modelling select H ⊆ E F decoding apply any given h ∈ H training select h ∈ H 4 / 15

Modelling: State Of The Art H = { h G , LM ,θ | G ∈ G , LM ∈ LM , θ ∈ R 2 } where h G , LM ,θ : f �→ D ( G ) R F E 5 / 15

Modelling: State Of The Art H = { h G , LM ,θ | G ∈ G , LM ∈ LM , θ ∈ R 2 } where h G , LM ,θ : f �→ D ( G ) R π F π E F E 5 / 15

Modelling: State Of The Art H = { h G , LM ,θ | G ∈ G , LM ∈ LM , θ ∈ R 2 } where h G , LM ,θ : f �→ D ( G ) R π F π E F E 5 / 15

Modelling: State Of The Art H = { h G , LM ,θ | G ∈ G , LM ∈ LM , θ ∈ R 2 } where h G , LM ,θ : f �→ D ( G ) R π F π E F E 5 / 15

Modelling: State Of The Art H = { h G , LM ,θ | G ∈ G , LM ∈ LM , θ ∈ R 2 } where � � h G , LM ,θ : f �→ π E D ( G ) R π F π E F E 5 / 15

Modelling: State Of The Art H = { h G , LM ,θ | G ∈ G , LM ∈ LM , θ ∈ R 2 } where � � � G � ( d ) θ 1 · � LM � ( π E ( d )) θ 2 h G , LM ,θ : f �→ π E D ( G ) R π F π E F E 5 / 15

Modelling: State Of The Art H = { h G , LM ,θ | G ∈ G , LM ∈ LM , θ ∈ R 2 } where � � argmax d : π F ( d )= f � G � ( d ) θ 1 · � LM � ( π E ( d )) θ 2 h G , LM ,θ : f �→ π E D ( G ) R π F π E F E 5 / 15

Synchronous Context-Free Grammar π 1 : S → � S X, S X � π 2 : S → � X, X � π 3 : X → � yu X 1 you X 2 , have X 2 with X 1 � π 4 : X → � X 1 de X 2 , the X 2 that X 1 � π 5 : X → � X zhiyi, one of X � π 6 : X → � Aozhou, Australia � π 7 : X → � Beihan, North Korea � π 8 : X → � shi, is � π 9 : X → � bangjiao, diplomatic relations � π 10 : X → � shaoshu guojia, few countries � 6 / 15

Derivation � S, S � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � π 5 ⇒ � Aozhou shi X zhiyi, Australia is one of X � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � π 5 ⇒ � Aozhou shi X zhiyi, Australia is one of X � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � π 5 ⇒ � Aozhou shi X zhiyi, Australia is one of X � π 4 ⇒ � Aozhou shi X 1 de X 2 zhiyi, Australia is one of the X 2 that X 1 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � π 5 ⇒ � Aozhou shi X zhiyi, Australia is one of X � π 4 ⇒ � Aozhou shi X 1 de X 2 zhiyi, Australia is one of the X 2 that X 1 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � π 5 ⇒ � Aozhou shi X zhiyi, Australia is one of X � π 4 ⇒ � Aozhou shi X 1 de X 2 zhiyi, Australia is one of the X 2 that X 1 � π 3 ⇒ � Aozhou shi yu X 1 you X 0 de X 2 zhiyi, Australia is one of the X 2 that have X 0 with X 1 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � π 5 ⇒ � Aozhou shi X zhiyi, Australia is one of X � π 4 ⇒ � Aozhou shi X 1 de X 2 zhiyi, Australia is one of the X 2 that X 1 � π 3 ⇒ � Aozhou shi yu X 1 you X 0 de X 2 zhiyi, Australia is one of the X 2 that have X 0 with X 1 � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � π 5 ⇒ � Aozhou shi X zhiyi, Australia is one of X � π 4 ⇒ � Aozhou shi X 1 de X 2 zhiyi, Australia is one of the X 2 that X 1 � π 3 ⇒ � Aozhou shi yu X 1 you X 0 de X 2 zhiyi, Australia is one of the X 2 that have X 0 with X 1 � π 7 ⇒ � Aozhou shi yu Beihan you X 0 de X 2 zhiyi, Australia is one of the X 2 that have X 0 with North Korea � 7 / 15

Derivation � S, S � π 1 ⇒ � S X, S X � π 1 ⇒ � S X 1 X 2 , S X 1 X 2 � π 2 ⇒ � X 0 X 1 X 2 , X 0 X 1 X 2 � π 6 ⇒ � Aozhou X 1 X 2 , Australia X 1 X 2 � π 8 ⇒ � Aozhou shi X, Australia is X � π 5 ⇒ � Aozhou shi X zhiyi, Australia is one of X � π 4 ⇒ � Aozhou shi X 1 de X 2 zhiyi, Australia is one of the X 2 that X 1 � π 3 ⇒ � Aozhou shi yu X 1 you X 0 de X 2 zhiyi, Australia is one of the X 2 that have X 0 with X 1 � π 7 ⇒ � Aozhou shi yu Beihan you X 0 de X 2 zhiyi, Australia is one of the X 2 that have X 0 with North Korea � 7 / 15