18299342. Co-attentive Fusion with Unified Label Graph Representation for Low-resource Text Classification simplified abstract (Robert Bosch GmbH)
Contents
Co-attentive Fusion with Unified Label Graph Representation for Low-resource Text Classification
Organization Name
Inventor(s)
Co-attentive Fusion with Unified Label Graph Representation for Low-resource Text Classification - A simplified explanation of the abstract
This abstract first appeared for US patent application 18299342 titled 'Co-attentive Fusion with Unified Label Graph Representation for Low-resource Text Classification
The Co-attentive Fusion with Unified Label Graph Representation (CoFuLaG) is a text classification framework that involves two stages.
- In the first stage, a unified label graph is created, combining structured knowledge from a graph with unstructured knowledge from label descriptions.
- The unified label graph helps incorporate more accurate label semantics into text classification by explicitly modeling relationships between labels.
- The second stage involves a text classification model using the unified label graph to predict the output label for a given input text.
Key Features and Innovation:
- Construction of a unified label graph combining structured and unstructured knowledge.
- Explicit modeling of label relationships for more accurate text classification.
Potential Applications:
- Enhanced text classification in various industries such as e-commerce, healthcare, and finance.
Problems Solved:
- Improved accuracy in text classification by incorporating more precise label semantics.
Benefits:
- Better understanding of subtle differences between labels.
- Identification of exceptional sub-concepts under a label.
Commercial Applications:
- SEO-optimized text classification models for improved search engine results in various industries.
Questions about CoFuLaG: 1. How does CoFuLaG improve text classification accuracy? 2. What industries can benefit the most from using CoFuLaG in their text classification processes?
Frequently Updated Research: Stay updated on the latest advancements in text classification frameworks like CoFuLaG to ensure optimal performance in various applications.
Original Abstract Submitted
A text classification framework is disclosed, referred to as Co-attentive Fusion with Unified Label Graph Representation (CoFuLaG). The text classification framework is a two-stage process. In a first stage, a unified label graph is constructed that includes relevant label semantic information. The unified label graph advantageously unifies structured knowledge represented by a graph with unstructured knowledge given by label descriptions, thereby incorporating more adequate label semantics into text classification. The unified label graph advantageously models relations between labels explicitly, which can help to clarify subtle differences between two labels and identify exceptional sub-concepts under a label. In a second stage, a text classification model predicts an output label that should be applied to an input text using the unified label graph.
