Computer method and apparatus for segmenting text streams

• US 6,772,120 B1
• Filed: 11/21/2000
• Issued: 08/03/2004
• Est. Priority Date: 11/21/2000
• Status: Expired due to Fees

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Moreno, Pedro J., Blei, David M.
• Primary Examiner(s): {haeck over (S)}mits, T{overscore (a)}livaldis Ivars
• Assistant Examiner(s): SPOONER, LAMONT M
• Application Number:
  US09/718,177
• Time in Patent Office: 1,351 Days
• Field of Search: 704/236, 704/240, 704/242, 704/245, 704/250, 704/255, 704/256, 704/1, 704/9, 704/257
• US Class Current: 704/256
• CPC Class Codes: G06F 40/216 using statistical methods

Abstract

Computer method and apparatus for segmenting text streams is disclosed. Given is an input text stream formed of a series of words. A probability member provides working probabilities that a group of words is of a topic selected from a plurality of predetermined topics. The probability member accounts for relationships between words. A processing module receives the input text stream and using the probability member determines probability of certain words in the input text stream being of a same topic. As such, the processing module segments the input text stream into single topic groupings of words, where each grouping is of a respective single topic.

Claims

1. Computer apparatus for segmenting text streams, comprising:

an input text stream formed of a series of words;

a probability member providing working probabilities of a group of words being of a topic selected from a plurality of predetermined topics, said probability member accounting for relationship between words, and wherein the probability member is a Hidden Markov Model combined with an Aspect model; and

a processing module coupled to receive the input text stream and using the probability member determining probability of certain words in the input text stream being of a same topic such that the processing module segments the input text stream into single topic groupings of words, where each grouping is of a respective single topic.

2. Computer apparatus as claimed in claim 1 wherein the probability member is fully automated such that working probabilities are provided in a manner free of heuristics or labeled data.

3. A method for segmenting text streams, comprising the computer implemented steps of:

receiving an input text stream formed of a series of words;

providing working probabilities of a group of words being of a topic selected from a plurality of predetermined topics, said working probabilities accounting for relationship between words, and wherein the step of providing working probabilities includes combining a Hidden Markov Model with an Aspect model such that use of the Aspect model is extended to text segmentation through the Hidden Markov Model; and

using the working probabilities, determining probability of certain words in the input text stream being of a same topic such that the input text stream is segmented into single topic groupings of words, where each grouping is of a respective single topic.

4. A method as claim 3 wherein the step of providing working probabilities is fully computer automated and includes providing working probabilities in a manner free of heuristics or labeled data.