Text Topic Determination via Word Dependency Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurately determining text topics in natural language processing is challenging due to the complexity of word dependencies and semantic relationships within large datasets.
Innovation Solution
A computer-implemented method and apparatus that determine a text topic by analyzing a word sequence and graph structure representing word dependencies, using a topic distribution based on the word sequence and graph structure to identify the text topic.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional text topic determination methods are used, then the processing is simpler, but the accuracy of topic determination deteriorates due to inability to capture word dependencies
Solution Approach 1:
The patent segments the text into a word sequence and separately identifies spaced words between each pair of words. This segmentation allows the method to capture both individual word meanings and their positional relationships, improving topic determination accuracy while managing complexity through structured decomposition of the text analysis task.
Solution Approach 2:
The patent introduces a graph structure dimension to represent word dependencies, transforming the traditional linear text analysis into a multi-dimensional representation. By mapping words and their spaced relationships onto a graph structure, the method captures semantic dependencies that linear methods miss, thereby improving accuracy without proportionally increasing complexity.
2Measurement precision
If word dependencies are considered in detail, then topic determination accuracy improves, but the computational complexity increases
Solution Approach 1:
The patent extracts only the necessary dependency information by identifying spaced words between specific pairs of words in the sequence, rather than analyzing all possible word relationships. This selective extraction captures essential semantic dependencies for topic determination while avoiding the computational burden of complete dependency analysis.
Solution Approach 2:
The method applies partial action by focusing analysis on spaced words that are most relevant to topic determination, rather than processing all word relationships equally. This approach achieves sufficient accuracy for topic identification without the excessive computational cost of exhaustive dependency analysis.
Data Source
AI summary
A method for determining a text topic includes: after a word sequence corresponding to a text to be processed and a number of spaced words in the text to be processed between each two words in the word sequence are determined, a graph structure corresponding to the text to be processed may be determined based on the number of spaced words between each two words in the text to be processed, a topic distribution corresponding to the text may be determined based on the word sequence and the graph structure, a topic corresponding to the text may be determined based on the topic distribution.