Download presentation

Presentation is loading. Please wait.

Published byDamian Eustace Modified about 1 year ago

1
Intro to NLP - J. Eisner1 Phonology [These slides are missing most examples and discussion from class …]

2
Intro to NLP - J. Eisner2 “kats” “dawgz” “roziz” “kisiz” Pronunciation What is Phonology? cat + -s dog + -s rose + -s kiss + -s cats dogs roses kisses Spelling How do you pronounce a sequence of morphemes? Especially, how & why do you fix up the pronunciation at the seams between morphemes? why? phonology doesn’t care about the spelling (that’s just applied morphology)

3
Intro to NLP - J. Eisner3 “næpt” “næbd” “nadid” “natid” Pronunciation What is Phonology? nap + -t nab + -t nod + -t knot + -t napped nabbed nodded knotted Spelling Actually, these are pronounced identically: na∂ I d thanks to the English “flapping” rule (similarly: ladder/latter, bedding/betting)

4
Intro to NLP - J. Eisner4 “Trisyllabic Shortening” in English What is Phonology? divine divinity futile futility senile senility satire satirical decide decision wild wilderness serene serenity supreme supremity obscene obscenity obese *obesity (and similarly for other vowels)

5
Intro to NLP - J. Eisner5 What is Phonology? A function twixt head and lip What class of functions is allowed ? Differs from one language to next Often complicated, but not arbitrary Comp Sci: How to compute, invert, learn? Morphology (head) Phonological mapping Articulation (mouth) underlying phonemes surface phones ree-ZIYN reh-zihg-NAY-shun resign resign + -ation

6
Intro to NLP - J. Eisner6 Successive Fixups for Phonology Chomsky & Halle (1968) Stepwise refinement of a single form How to handle “resignation” example? That is, O = f( I ) = g 3 (g 2 (g 1 ( I ))) Function composition (e.g., transducer composition) Rule 1 Rule 2 input (I) output (O) Rule 3

7
Intro to NLP - J. Eisner7 How to Give Orders Directions version: Break two eggs into a medium mixing bowl. Remove this tab first. On the last day of each month, come to this office and pay your rent. Rules version: No running in the house is allowed. All dogs must be on a leash. Rent must be paid by the first day of each month. In rules version, describe what a good solution would look like, plus a search procedure for finding the best solution). Where else have we seen this? successive fixup (derivation) successive winnowing (optimization) example courtesy of K. Crosswhite

8
Intro to NLP - J. Eisner8 Optimality Theory for Phonology Prince & Smolensky (1993) Alternative to successive fixups Successive winnowing of candidate set Gen Constraint 1 Constraint 2 Constraint 3 input... output

9
Intro to NLP - J. Eisner9 Optimality Theory “Tableau” constraint would prefer A, but only allowed to break tie among B,D,E = candidate violates constraint twice (weight 2)

10
Intro to NLP - J. Eisner10 Optimality Theory for Phonology Gen Constraint 1 Constraint 2 Constraint 3 input (I)... output (O) adds weights to candidates adds weights to candidates best paths (several may tie) best paths (breaks some ties)

11
Intro to NLP - J. Eisner11 When do we prune back to best paths? Optimality Theory: At each intermediate stage Noisy channel: After adding up all weights... output (O)

12
Intro to NLP - J. Eisner12 Why does order matter? Optimality Theory: Each machine (FSA) can choose only among outputs that previous machines liked best Noisy channel: Each machine (FST) alters the output produced by previous machines... output (O)

13
Intro to NLP - J. Eisner13 Final Remark on OT Repeated best-paths only works for a single input Better to build full FST for I O (invertible) Can do this e.g. if every constraint is binary: Assigns each candidate either 1 star (“bad”) or 0 stars (“good”) Gen Constraint 1 Constraint 2 Constraint 3 input (I)... output (O)

14
Intro to NLP - J. Eisner14 Optimality Theory “Tableau” all surviving candidates violate constraint 3, so we can’t eliminate any

Similar presentations

© 2016 SlidePlayer.com Inc.

All rights reserved.

Ads by Google