PartofSpeech Tagging A Canonical FiniteState Task 600 465

  • Slides: 9
Download presentation
Part-of-Speech Tagging A Canonical Finite-State Task 600. 465 - Intro to NLP - J.

Part-of-Speech Tagging A Canonical Finite-State Task 600. 465 - Intro to NLP - J. Eisner 1

Three Finite-State Approaches 1. Noisy Channel Model (HMM) 2. Deterministic baseline tagger composed with

Three Finite-State Approaches 1. Noisy Channel Model (HMM) 2. Deterministic baseline tagger composed with a cascade of fixup transducers 3. Nondeterministic tagger composed with a cascade of finite-state automata that act as filters 600. 465 - Intro to NLP - J. Eisner 2

Three Finite-State Approaches 1. Noisy Channel Model (HMM) 2. Deterministic baseline tagger composed with

Three Finite-State Approaches 1. Noisy Channel Model (HMM) 2. Deterministic baseline tagger composed with a cascade of fixup transducers 3. Nondeterministic tagger composed with a cascade of finite-state automata that act as filters 600. 465 - Intro to NLP - J. Eisner 3

Another FST Paradigm: Successive Fixups n Like successive markups but alter Morphology Phonology Part-of-speech

Another FST Paradigm: Successive Fixups n Like successive markups but alter Morphology Phonology Part-of-speech tagging … 600. 465 - Intro to NLP - J. Eisner 3 p Fi xu p 2 1 p xu Fi al In iti input an no ta tio § § § output 4

figure from Brill’s thesis Transformation-Based Tagging (Brill 1995) 600. 465 - Intro to NLP

figure from Brill’s thesis Transformation-Based Tagging (Brill 1995) 600. 465 - Intro to NLP - J. Eisner 5

figure from Brill’s thesis Transformations Learned Baseline. Tag* NN @ VB // TO _

figure from Brill’s thesis Transformations Learned Baseline. Tag* NN @ VB // TO _ VBP @ VB //. . . _ etc. Compose this cascade of FSTs. Gets a big FST that does the initial tagging and the sequence of fixups “all at once. ” 600. 465 - Intro to NLP - J. Eisner 6

figure from Brill’s thesis Initial Tagging of OOV Words 600. 465 - Intro to

figure from Brill’s thesis Initial Tagging of OOV Words 600. 465 - Intro to NLP - J. Eisner 7

Three Finite-State Approaches 1. Noisy Channel Model (statistical) 2. Deterministic baseline tagger composed with

Three Finite-State Approaches 1. Noisy Channel Model (statistical) 2. Deterministic baseline tagger composed with a cascade of fixup transducers 3. Nondeterministic tagger composed with a cascade of finite-state automata that act as filters 600. 465 - Intro to NLP - J. Eisner 8

Variations § Multiple tags per word § Transformations to knock some of them out

Variations § Multiple tags per word § Transformations to knock some of them out § How to encode multiple tags and knockouts? § Use the above for partly supervised learning § Supervised: You have a tagged training corpus § Unsupervised: You have an untagged training corpus § Here: You have an untagged training corpus and a dictionary giving possible tags for each word 600. 465 - Intro to NLP - J. Eisner 9

PartofSpeech Tagging A Canonical FiniteState Task 600 465PartofSpeech Tagging A Canonical FiniteState Task 600 465
PartofSpeech Tagging A Canonical FiniteState Task 600 465PartofSpeech Tagging A Canonical FiniteState Task 600 465
PartofSpeech POS tagging See Eric Brill Partofspeech taggingPartofSpeech POS tagging See Eric Brill Partofspeech tagging
PartOfSpeech Tagging Radhika Mamidi POS tagging Tagging meansPartOfSpeech Tagging Radhika Mamidi POS tagging Tagging means
Deterministic PartofSpeech Tagging with FiniteState Transducers by EmmanuelDeterministic PartofSpeech Tagging with FiniteState Transducers by Emmanuel
Controllable Canonical Form Controllable Canonical Form Controllable CanonicalControllable Canonical Form Controllable Canonical Form Controllable Canonical
FiniteState Methods 600 465 Intro to NLP JFiniteState Methods 600 465 Intro to NLP J
FiniteState and the Noisy Channel 600 465 IntroFiniteState and the Noisy Channel 600 465 Intro