18123425. SUMMARY GENERATION BASED ON COMPARISON OBJECTS simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
SUMMARY GENERATION BASED ON COMPARISON OBJECTS
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Yi Chen Zhang of Shanghai (CN)
Chuan Le Zheng of Shanghai (CN)
SUMMARY GENERATION BASED ON COMPARISON OBJECTS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18123425 titled 'SUMMARY GENERATION BASED ON COMPARISON OBJECTS
The abstract describes a method for generating summaries based on text descriptions of a target object and at least one comparison object. Semantic vectors are extracted from the text descriptions using a deep learning model, which are then input to a generator model trained with an adversarial machine learning technique to output a summary of the target object that highlights its unique characteristics compared to the comparison object.
- Semantic vectors extracted from text descriptions
- Generator model trained with adversarial machine learning
- Output summary highlighting unique characteristics of target object
- Excludes characteristics of comparison object
- Utilizes deep learning model for semantic extraction
Potential Applications: - Automated summarization of product descriptions - Enhancing search engine results with concise summaries - Improving content generation for e-commerce websites
Problems Solved: - Streamlining the process of summarizing text descriptions - Providing users with quick and accurate information - Enhancing the efficiency of content creation
Benefits: - Saves time and effort in summarizing text data - Increases user engagement with concise summaries - Improves search engine optimization for websites
Commercial Applications: Title: Automated Text Summarization Technology for E-commerce Websites This technology can be used to automatically generate product summaries for online stores, improving the user experience and increasing conversion rates. It can also be integrated into search engines to provide users with quick and relevant information.
Questions about Automated Text Summarization Technology: 1. How does this technology compare to traditional methods of summarization? This technology utilizes deep learning models to extract semantic vectors and generate summaries, offering a more efficient and accurate approach compared to manual summarization methods.
2. What are the potential challenges in implementing this technology on a large scale? Implementing this technology on a large scale may require significant computational resources and data processing capabilities to handle the volume of text data for summarization.
Original Abstract Submitted
Summary generation based on comparison objects can include receiving text descriptions of a target object and at least one comparison object. Semantic vectors from the text descriptions can be obtained, using a deep learning based semantic extraction model. The semantic vectors can be input to a generator model trained using an adversarial machine learning technique, the generator model outputting a text summary of the target object describing only unique characteristics of the target object different from characteristics of the at least one comparison object and excluding the characteristics of the at least one comparison object.