Textual Information Access: Statistical Models

Index

A

a priori Bayesian

smoothing

alignment

annotation

automatic

speech recognition

summarization

summarization of opinions

summarization of text

B

backward algorithm

bag of words

vs sequence

Baum-Wels algorithm

Bayes’ rule

Bernoulli

distribution

model

binary independence

model

retrieval (BIR)

bipartisan

ranking

bisegment

BLEU

BM25

burstiness

C

categorization

characteristic

features

function

classification

documents according to their opinion

clustering

unsupervised clustering

co-citations

combinatorial optimization

conditional

entropy

independence

Markovian field

probability

Random Field, see conditional Markovian fields

convex upper bound

core

CRF, see conditional Markovian fields

critical pair classification

cross validation

D

data

fusion

unification

diffusion

kernels

Dirichlet

distribution

smoothing

discriminant models

distortion

divergence from randomness (DFR)

document filtering

dynamic programming

E

EM algorithm

empirical error rate

entropy maximum

evaluation

expectation of a random variable

exponential family

F

F-measure

false negative

false positive

fertility

fisher

kernels

information

forward algorithm

forward-backward algorithm

function words

G

Gaussian

mixing

generalized

linear model

vector model

generative model

vs discriminative

Gibbs sampling

gradient descent

gram matrix

graph kernel

graphical model

H

hidden Markov

chain

models

hierarchical

classification

concepts

model

HMM, see hidden Markov model

I

IBM model

IBM1

IBM2

IBM3

IBM4-IBM6

indexation

information

extraction ...