Unsupervised topic modeling for short texts

Patent metadata

Field	Value
Publication number	US-2016110343-A1
Application number	US-201414519427-A
Country	US
Kind code	A1
Filing date	Oct 21, 2014
Priority date	Oct 21, 2014
Publication date	Apr 21, 2016
Grant date	—

Abstract

Topics are determined for short text messages using an unsupervised topic model. In a training corpus created from a number of short text messages, a vocabulary of words is identified, and for each word a distributed vector representation is obtained by processing windows of the corpus having a fixed length. The corpus is modeled as a Gaussian mixture model in which Gaussian components represent topics. To determine a topic of a sample short text message, a posterior distribution over the corpus topics is obtained using the Gaussian mixture model.

First claim

What is claimed is:

1 . A method for determining a topic of a sample short text message, comprising:
by a computer, identifying a vocabulary of words in a corpus, the corpus comprising a plurality of training short text messages; by the computer, obtaining distributed vector representations of the words in the vocabulary by processing windows of the corpus having a fixed length; by the computer, estimating a plurality of Gaussian components of a Gaussian mixture model of the corpus using the distributed vector representations, the Gaussian components representing corpus topics; by the computer, receiving a sample short text message comprising words in the vocabulary; and by the computer, determining the topic of the sample short text message based on a posterior distribution over the corpus topics for the sample short text message, the posterior distribution obtained using the Gaussian mixture model.

2 . The method of claim 1 , wherein obtaining distributed vector representations of the words in the vocabulary further comprises applying a continuous bag of words model to process the windows of the corpus.

3 . The method of claim 2 , wherein applying a continuous bag of words model further comprises using a log-linear model.

4 . The method of claim 1 , wherein obtaining distributed vector representations of the words in the vocabulary further comprises applying a methodology to process the windows of the corpus, the methodology being selected from a group of methodologies consisting of deep neural network, latent semantic indexing, log-linear model, feedforward neural network, convolutional neural network and recurrent neural network.

5 . The method of claim 1 wherein identifying the vocabulary of words in a corpus further comprises using hierarchical sampling to reduce the vocabulary.

6 . The method of claim 5 wherein the hierarchical sampling eliminates words having fewer than five occurrences.

7 . The method of claim 1 wherein the plurality of training short text messages has an average text length of between 12 and 16 words.

8 . The method of claim 1 wherein estimating the plurality of Gaussian components further comprises estimating means, covariances and mixture weights for each Gaussian component using an expectation-maximization algorithm.

9 . The method of claim 8 wherein the covariances are estimated using a covariance matrix approximation wherein the covariances are diagonal matrices.

10 . The method of claim 1 wherein the sample short text message has fewer than 20 words.

11 . The method of claim 1 wherein the posterior distribution over the corpus topics for the short message is determined by evaluating:

k
*

=

arg



max



θ
k



p


(
k
)



∏

i
=
1

N





p


(

w
i
′

|
k

)

where k* is a posterior distribution for a topic k, θ k denotes the parameters for the k th Gaussian component of the Gaussian mixture model, w i ′ is the i th word in the sample short text message and the probabilities p(k) and p(w i ′|k) are obtained from the Gaussian mixture model.

12 . The method of claim 1 , wherein identifying the vocabulary of words in the corpus further comprises representing a phrase of words within the corpus by a single code word to minimize a description length of the corpus.

13 . A message topic trend alert system of a communications network, comprising:
at least one interface to the communications network configured for receiving short text messages transmitted within the short message communications network; at least one processor; and at least one computer readable storage device having stored thereon computer readable instructions that, when executed by the at least one processor, cause the at least one processor to perform operations for generating an alert based on a message topic trend, comprising:
identifying a vocabulary of words in a corpus, the corpus comprising a plurality of training short text messages;
obtaining distributed vector representations of the words in the vocabulary by processing windows of the corpus having a fixed length;
estimating a plurality of Gaussian components of a Gaussian mixture model of the corpus using the distributed vector representations, the Gaussian components representing corpus topics;
receiving a plurality of sample short text messages comprising words in the vocabulary;
determining topics of the sample short text messages based on a posterior distribution over the corpus topics for the sample short text messages, the posterior distribution obtained using the Gaussian mixture model;
identifying a trend in topics of the short text messages; and
generating an alert based on the trend.

14 . The system of claim 13 , wherein obtaining distributed vector representations of the words in the vocabulary further comprises applying a continuous bag of words model to process the windows of the corpus.

15 . The system of claim 14 , wherein applying a continuous bag of words model further comprises using a log-linear model.

16 . The system of claim 13 wherein identifying the vocabulary of words in a corpus further comprises using hierarchical sampling to reduce the vocabulary.

17 . The system of claim 13 wherein estimating the plurality of Gaussian components further comprises estimating means, covariances and mixture weights for each Gaussian component using an expectation-maximization algorithm.

18 . The system of claim 13 wherein the posterior distribution over the corpus topics for the short message is determined by evaluating:

k
*

=

arg

max

θ
k



Assignees

• At & T Ip I Lp

Inventors

• Kumar Rangarajan Sridhar Vivek

Classifications

• H04W4/14 Primary

  Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD] · CPC title

• G10L25/30

  using neural networks · CPC title

• G06F40/216 Primary

  using statistical methods · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F17/2715 Primary

  Physics · mapped topic