18158871. METHOD AND SYSTEM FOR AUTOMATED Q&A VIA ENRICHED TEXT SIMILARITY simplified abstract (Verizon Patent and Licensing Inc.)

From WikiPatents
Jump to navigation Jump to search

METHOD AND SYSTEM FOR AUTOMATED Q&A VIA ENRICHED TEXT SIMILARITY

Organization Name

Verizon Patent and Licensing Inc.

Inventor(s)

Miruna Jayakrishnasamy of Vellore (IN)

Prakash Ranganathan of Tamilnadu (IN)

METHOD AND SYSTEM FOR AUTOMATED Q&A VIA ENRICHED TEXT SIMILARITY - A simplified explanation of the abstract

This abstract first appeared for US patent application 18158871 titled 'METHOD AND SYSTEM FOR AUTOMATED Q&A VIA ENRICHED TEXT SIMILARITY

The present teaching involves a hierarchical and explainable (HE) similarity and its application. A target text is identified based on a source text, and the HE similarity characterizes the similarity between the two texts using multiple assessment categories.

  • The HE similarity is computed based on linguistic features of source and target phrases.
  • A HE feature vector is constructed with similarity scores at phrase, word, and character levels.
  • The HE similarity is used to determine the relationship between the target text and the source text.

Potential Applications: - Text analysis and comparison in natural language processing - Plagiarism detection and content verification - Machine translation and language understanding systems

Problems Solved: - Enhancing the accuracy of text similarity assessments - Providing explainable results in text comparison tasks

Benefits: - Improved accuracy in identifying similarities between texts - Enhanced transparency in text analysis processes

Commercial Applications: Title: Enhanced Text Comparison Technology for Content Verification This technology can be used in academic institutions, publishing houses, and online content platforms to ensure the originality and authenticity of written content.

Questions about the technology: 1. How does the HE similarity differ from traditional text similarity metrics? 

  - The HE similarity provides a more detailed and transparent analysis of text similarities compared to traditional methods.

2. What are the key features that make this technology stand out in the field of text analysis? 

  - The use of hierarchical and explainable features sets this technology apart by providing a deeper understanding of text relationships.


Original Abstract Submitted

The present teaching relates to a hierarchical and explainable (HE) similarity and use thereof. A target text is identified based on a source text. A HE similarity characterizes the similarity between the source and target texts in terms of multiple assessment categories and is computed based on source and target phrases generated via linguistic features. A HE feature vector is constructed with similarity scores at phrase, word, and character levels. The HE similarity is computed based on the HE feature vector and used to determine whether the target text related to the source text. The HE similarity is used to determine whether the target text relates to the source text.

Retrieved from "http://wikipatents.org/index.php?title=18158871._METHOD_AND_SYSTEM_FOR_AUTOMATED_Q%26A_VIA_ENRICHED_TEXT_SIMILARITY_simplified_abstract_(Verizon_Patent_and_Licensing_Inc.)&oldid=205848"