This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: D R A F T Speech and Language Processing: An introduction to natural language processing, computational linguistics, and speech recognition. Daniel Jurafsky & James H. Martin. Copyright c circlecopyrt 2007, All rights reserved. Draft of September 19, 2007. Do not cite without permission. 11 COMPUTATIONAL PHONOLOGY bidakupadotigolabubidakutupiropadotigolabutupirobidaku... Word segmentation stimulus (Saffran et al., 1996a) Recall from Ch. 7 that phonology is the area of linguistics that describes the sys- tematic way that sounds are differently realized in different environments, and how this system of sounds is related to the rest of the grammar. This chapter introduces computational phonology , the use of computational models in phonological theory. COMPUTATIONAL PHONOLOGY One focus of computational phonology is on computational models of phonological representation, and on how to use phonological models to map from surface phonolog- ical forms to underlying phonological representation. Models in (non-computational) phonological theory are generative; the goal of the model is to represent how an under- lying form can generate a surface phonological form. In computation, we are generally more interested in the alternative problem of phonological parsing ; going from surface form to underlying structure. One major tool for this task is the finite-state automaton, which is employed in two families of models: finite-state phonology and optimality theory . A related kind of phonological parsing task is syllabification : the task of assigning syllable structure to sequences of phones. Besides its theoretical interest, syllabifi- cation turns out to be a useful practical tool in aspects of speech synthesis such as pronunciation dictionary design. We therefore summarize a few practical algorithms for syllabification. Finally, we spend the remainder of the chapter on the key problem of how phono- logical and morphological representations can be learned. 11.1 F INITE-S TATE P HONOLOGY Ch. 3 showed that spelling rules can be implemented by transducers. Phonological rules can be implemented as transducers in the same way; indeed the original work by Johnson (1972) and Kaplan and Kay (1981) on finite-state models was based on phonological rules rather than spelling rules. There are a number of different models of computational phonology that use finite automata in various ways to realize phono- D R A F T 2 Chapter 11. Computational Phonology logical rules. We will describe the two-level morphology of Koskenniemi (1983) first mentioned in Ch. 3. Lets begin with the intuition, by seeing the transducer in Fig. 11.1 which models the simplified flapping rule in (11.1): /t/ [dx] / V V (11.1) 2 1 3 other other V:@ V:@ V:@ V:@ t:dx t t t V:@ V:@ other Figure 11.1 Transducer for English Flapping: ARPAbet dx indicates a flap, and the other symbol means any feasible pair not used elsewhere in the transducer. @ means any symbol not used elsewhere on any arc.any symbol not used elsewhere on any arc....
View Full Document
- Fall '11
- Natural Language Processing