US 9,069,798 B2Granted

Method of text classification using discriminative topic transformation

AssigneeMitsubishi Electric Research Laboratories, Inc.

InventorsJohn R. Hershey, Jonathan Le Roux

Life of this patent

Estimating the term…

Loading patent…

Abstract

Text is classified by determining text features from the text, and transforming the text features to topic features. Scores are determined for each topic features using a discriminative topic model. The model includes a classifier that operates on the topic features, wherein the topic features are determined by the transformation from the text features, and the transformation is optimized to maximize the scores of a correct class relative to the scores of incorrect classes. Then, a class label with a highest score is selected for the text. In situations where the classes are organized in a hierarchical structure, the discriminative topic models apply to classes at each level conditioned on previous levels and scores are combined across levels to evaluate the highest scoring class labels.

Claims16

Dependent claims

A method for classifying text, comprising-steps of:

acquiring text as input data in a processor, wherein the text is derived from one or more hypotheses from an automatic speech recognition system operating on a speech signal;
determining text features from the text x, wherein the text features are ƒj,k(x,y);
transforming the text features to topic features, wherein the transforming is according to gl,k(x,y)=hl(ƒ1,k(x,y), . . . ,ƒJ,k(x,y)),
where j is an index for a type of feature, k is an index of a class associated with the feature, y is a hypothesis of the class label, and hl(•) is a function that transforms the text features, and l is an index of the topic features;
determining scores from the topic features, wherein the determining steps use a model, wherein the model is a discriminative topic model comprising a classifier operating on the topic features, and the transforming is optimized to maximize the scores of a correct class relative to the scores of incorrect classes, wherein the discriminative topic model is
max
Λ
,
A
⁢
{
log
⁡
(
p
Λ
,
A
⁡
(
y
❘
x
)
)
-
α
⁢
∑
l
,
k
⁢
⁢

λ
l
,
k

2
-
β
⁢
∑
l
,
k
⁢
⁢

λ
l
,
k

-
γ
⁢
∑
l
⁢
⁢
(
∑
j
⁢
⁢

A
l
,
j

)
2
}
where α, β, γ are weight, and Λ is a classification optimizing parameter;
selecting a set of class labels with highest scores for the text;
outputting the set of class labels to classify the text, wherein the steps are performed in the processor.

77 more elements

Dependencies are inferred from the claim text.