1 / 12

Deterministic Part-of-Speech Tagging with Finite-State Transducers

Deterministic Part-of-Speech Tagging with Finite-State Transducers. by Emmanuel Roche and Yves Schabes. 정 유 진 KLE Lab. CSE POSTECH 98. 10. 16. Introduction. Stochastic approaches to NLP have often been preferred to rule-based approaches

imala
Download Presentation

Deterministic Part-of-Speech Tagging with Finite-State Transducers

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Deterministic Part-of-Speech Tagging with Finite-State Transducers by Emmanuel Roche and Yves Schabes 정 유 진 KLE Lab. CSE POSTECH 98. 10. 16

  2. Introduction • Stochastic approaches to NLP have often been preferred to rule-based approaches • Eric Brill (1992) : rule-based tagger by inferring rules from a training corpus • rules are automatically acquired • require drastically less space than stochastic tagger • but, considerably slow •  Deterministic Finite-State Transducer • (Subsequential Transducer) CS730B Statistical NLP

  3. Overview of Brill’s Tagger • Structure of the tagger • Lexical tagger (Initial tagger) • Unknown word tagger • Contextual tagger • Inefficiency • Individual rules is compared at each token of the input (Fig.3) • Potential interaction between rules (Fig.1) • Complexity : RKn • R : # of contextual rules n : # of input words • K : max # of tokens which rules require CS730B Statistical NLP

  4. Finite-State Transducer (1) • Finite-State Transducer T = (, Q, i, F, E) •  : finite alphabet Q : finite set of states • i : initial state F : set of final state • E : set of transitions (q, a, w, q’) on Q (  {}) *Q • Deterministic F.S. Transducer T = (, Q, i, F, , , ) •  : deterministic state transition func. ( q  a = q’) •  : deterministic emission func. ( q  a = w’ ) •  : final emission func. ( (q) = w for q  F ) CS730B Statistical NLP

  5. Finite-State Transducer (2) • state transition function • d (q,a) = {q’ Q | w’  * and (q,a,w’,q’)  E} • emission function •  (q,a,q’) = {w’  * | (q,a,w’,q’)  E} CS730B Statistical NLP

  6. Construction of the Finite-State Tagger (1) • 1. Turn each contextual rule into a finite-state transducer • 2. Local extension of the transducer (algorithm of Fig.17) vbn vbd PRETAG np np/np vbn/vbd 0 1 2 np/np ?/? np/np ?/? 0 vbn/vbd 1 CS730B Statistical NLP

  7. Construction of the Finite-State Tagger (2) • 3. Combines all transducers into one single transducer • (algorithm of Elgot and Mezei) • 4. Transforming the obtained transducer into an equivalent • subsequential (deterministic) transducer (algorithm of Fig.21) • Advantage • Requires n steps to tag a sentence of length n, independently of the number of rules and the length of the context • Eliminate inefficiencies of Brill’s tagger CS730B Statistical NLP

  8. Local Extension Algorithm / 1 a/b b/c {1} transd 2 b/c 0 a/b b/d {2} transd 3 Fig.18 b/d {0} identity ?/? 4 a/b 0 b/b a/a {} transd ?/? {0,1} identity Fig.19 1 a/a 2 CS730B Statistical NLP

  9. Determinization Algorithm 1 a/b h/h 3 0 a/c e/e 2 h/bh Fig.13 (2, ) (0, ) a/ (1,b) (2,c) 0 1 2 e/ce Fig.22 CS730B Statistical NLP

  10. Lexical Tagger • The first step of the tagging process : looking up each word in a dictionary (Fig.9) • To achieve high speed : (Fig.10) • Represent the dictionary by a deterministic finite-state automaton • (algorithm of Revuz) • Advantage • fast access : 12,000 words / second • small storage space : 742Kb (ASCII form)  360Kb • Unknown words Tagger • same techniques used CS730B Statistical NLP

  11. Implementation of Finite-State Transducer • Represented by a two-dimensional table • row : states • column : alphabet of all possible input letters • content : output of the transition a . . . qn . . . w CS730B Statistical NLP

  12. Evaluation • Overall performance comparison (Fig.11) • Stochastic Tagger : Church’s trigram tagger (1988) • Rule-based Tagger : Brill’s tagger • All taggers were trained on the Brown corpus and used same lexicon of Fig.10 • Speeds of the different parts of finite-state tagger (Fig.12) • Low-level factors (storage access) dominate the computation CS730B Statistical NLP

More Related