124.11.lec17

124.11.lec17 - CS 124/LINGUIST 180: From Click to edit...

Info iconThis preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon
Click to edit Master subtitle style Dan Jurafsky Lecture 17: Machine Translation: Statistical MT Slides from Ray Mooney
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Slide from Ray Mooney Statistical MT Surprising: Intuition comes from the impossibility of translation Consider Hebrew adonai roi (“the lord is my shepherd”) for a culture without sheep or shepherds! Something fluent and understandable, but not faithful: “The Lord will look after me” Something faithful, but not fluent and nautral
Background image of page 2
Slide from Ray Mooney What makes a good translation Translators often talk about two factors we want to maximize: Faithfulness or fidelity How close is the meaning of the translation to the meaning of the original (Even better: does the translation cause the reader to draw the same inferences as the original would have) Fluency or naturalness How natural the translation is, just considering its fluency in the target language
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Slide from Ray Mooney Statistical MT: Faithfulness and Best-translation of a source sentence S: Developed by researchers who were originally in speech recognition at IBM Called the IBM model ö T = argmax T fluency( T )faithfulness( T , S )
Background image of page 4
Slide from Ray Mooney The IBM model Hmm, those two factors might look familiar… Yup, it’s Bayes rule: ö T = argmax T fluency( T )faithfulness( T , S ) ö T = argmax T P ( T ) P ( S | T )
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Slide from Ray Mooney More formally Assume we are translating from a foreign language sentence F to an English sentence E: F = f1, f2, f3,…, fm We want to find the best English sentence E-hat = e1, e2, e3,…, en E-hat = argmaxE P(E|F) = argmaxE P(F|E)P(E)/P(F) = argmaxE P(F|E)P(E) Translation Model Language Model
Background image of page 6
Slide from Ray Mooney The noisy channel model for MT
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Slide from Ray Mooney Fluency: P(T) How to measure that this sentence That car was almost crash onto me is less fluent than this one: That car almost hit me. Answer: language models (N-grams!) For example P(hit|almost) > P(was|almost) But can use any other more sophisticated model of grammar Advantage: this is monolingual knowledge!
Background image of page 8
Slide from Ray Mooney Faithfulness: P(S|T) French: ça me plait [that me pleases] English: that pleases me - most fluent I like it I’ll take that one How to quantify this? Intuition: degree to which words in one sentence are plausible translations of words in other sentence Product of probabilities that each word in target sentence would generate each word in source sentence.
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Slide from Ray Mooney Faithfulness P(S|T) Need to know, for every target language word, probability of it mapping to every source language word. How do we learn these probabilities? Parallel texts! Lots of times we have two texts that are translations of each other If we knew which word in Source Text mapped to each word in Target Text, we could just count!
Background image of page 10
Slide from Ray Mooney Faithfulness P(S|T) Sentence alignment: Figuring out which source language sentence maps to which target language sentence
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 12
This is the end of the preview. Sign up to access the rest of the document.

This document was uploaded on 06/01/2011.

Page1 / 100

124.11.lec17 - CS 124/LINGUIST 180: From Click to edit...

This preview shows document pages 1 - 12. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online