{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

# We model these by pretending they are generated by a

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: ky Word Alignment •  A mapping between words in F and words in E •  Simplifying assump1ons (for Model 1 and HMM alignments): •  one ­to ­many (not many ­to ­one or many ­to ­many) •  each French word comes from exactly one English word •  An alignment is a vector of length J, one cell for each French word •  The index of the English word that the French word comes from •  Alignment above is thus the vector A = [2, 3, 4, 4, 5, 6, 6] •  a1=2, a2=3, a3=4, a4=4… Dan Jurafsky Three representa\$ons of an alignment A = [2, 3, 4, 4, 5, 6, 6] Dan Jurafsky Alignments that don’t obey one ­to ­many restric\$on •  Many to one: •  Many to many: Dan Jurafsky One addi\$on: spurious words •  A word in the Spanish (French, foreign) sentence that doesn’t align with any word in the English sentence is called a spurious word. •  We model these by pretending they are generated by a NULL English word e0 : A = 1, 3, 4, 4, 4, 0, 5, 7, 6 Dan Jurafsky Resul\$ng alignment A = [1, 3, 4, 4, 4, 0, 5, 7, 6] 18 Dan Jurafsky Compu\$ng word alignments •  Word alignments are the basis for most transla1on algorithms •  Given two sentences F and E, ﬁnd a good alignment •  But a word ­alignment algorithm can also be part of a mini ­ transla1on model itself. P ( F | E ) = ! P ( F, A | E ) A •  One of the most basic alignment models is also a simplis1c transla1on model. Dan Jurafsky IBM Model 1 Peter Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, Robert L. Mercer. 1993. The Mathema1cs of Sta1s1cal Machine Transla1on: Parameter Es1ma1on. Computa1onal Linguis1cs 19:2, 263 ­311 •  First of 5 “IBM models” •  CANDIDE, the ﬁrst complete SMT...
View Full Document

{[ snackBarMessage ]}

Ask a homework question - tutors are online