Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Reliability Steven Abney

Summary: Reliability
Steven Abney
Universitšat Tšubingen
The usual approach to stochastic parsing is to `reverse' a model of stochastic
generation. For example, a stochastic context-free grammar (SCFG) G defines a
stochastic process for generating sentences. A stochastic choice is made at each
derivation step, and the probability P(d) of the derivation is the joint probability
of the stochastic choices made. P(d, x), the probability of producing derivation
d and in the process deriving sentence x, is P(d) if d is in fact a derivation of
x, and 0 otherwise. P(x) is d P(d, x). To parse a sentence x, we choose that
derivation d for which the conditional probability P(d|x) of d given the sentence
x is at a maximum, where P(d|x) is defined as P(d, x)/P(x).
However, there is reason to believe that no SCFG provides an acceptable
approximation of P(d|x) for English. The basic problem is that SCFG's with
reasonable coverage of English typically assign significant probability to many
parses for each sentence. As a result, even if an SCFG G is successful in the
sense that the most-likely parse according to G is almost always the correct
parse, the most-likely parse will nonetheless have a probability significantly less
than one. In fact, it is probably a safe bet that, for SCFG's for English, the
average probability for the most-likely parse is a good deal less than 1/2.


Source: Abney, Steven P. - School of Information, University of Michigan


Collections: Computer Technologies and Information Sciences