Communicative Discourse Trees for Rhetorical Agreement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for discourse analysis, particularly in linguistics, fail to accurately represent rhetorical relationships between questions and answers due to insufficient rhetorical analysis, leading to inadequate matching of questions with appropriate answers in chatbot systems and dialog management.
Innovation Solution
The use of communicative discourse trees, which incorporate communicative actions and verb signatures to generate trees that represent rhetorical relationships, enabling improved matching and response generation in chatbots and search engines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If statistical-based solutions are used for discourse analysis, then the system can process language queries, but it fails to accurately determine rhetorical agreement between questions and answers
Solution Approach 1:
The patent segments discourse analysis into distinct components: rhetorical structure analysis (using RTD to identify question types and answer types) and communicative action analysis (using verb signatures to identify speech acts). This segmentation allows each component to be processed independently and then integrated, improving rhetorical agreement determination without overwhelming system complexity.
Solution Approach 2:
The patent introduces an intermediary layer that bridges statistical processing and rhetorical understanding. The RTD parser and verb signature matcher act as intermediaries that transform raw text into structured representations (question/answer types, communicative actions) that can be systematically compared to determine rhetorical agreement.
2Productivity
If existing discourse analysis methods are used, then basic language processing is achieved, but the system cannot match answers with questions due to insufficient rhetorical analysis
Solution Approach 1:
The patent performs preliminary analysis by parsing the rhetorical structure of questions and answers before attempting to match them. The RTD parser identifies question types (e.g., WH-questions, yes/no questions) and answer types (e.g., direct answers, indirect answers) in advance, creating a structured foundation for efficient matching that prevents loss of rhetorical information.
Solution Approach 2:
The patent transforms discourse data from unstructured text into structured parameters including rhetorical tree representations, question/answer type classifications, and verb signature extractions. This parameter transformation enables systematic comparison and matching while preserving rhetorical structure information that would be lost in statistical-only approaches.
3Measurement precision
If statistical-based solutions attempt to address topic and rhetorical agreement simultaneously, then comprehensive analysis is attempted, but rhetorical agreement is not properly addressed
Solution Approach 1:
The patent divides the analysis process into separate stages: rhetorical structure parsing (using RTD to build trees and identify question/answer types), communicative action extraction (using verb signatures to identify speech acts like assertion, question, command), and agreement determination (comparing the structured representations). This segmentation allows precise rhetorical agreement measurement without overwhelming complexity.
Solution Approach 2:
The patent introduces structured intermediate representations (rhetorical trees, type classifications, verb signature matches) that mediate between raw text and final agreement determination. These intermediaries preserve rhetorical information while enabling systematic processing, achieving accurate measurement without excessive complexity.
Data Source
AI summary
Systems, devices, and methods of the present invention calculate a rhetorical relationship between one or more sentences. In an example, a computer-implemented method accesses a sentence comprising a plurality of fragments. At least one fragment includes a verb and a words. Each word includes a role of the words within the fragment. Each fragment is an elementary discourse unit. The method generates a discourse tree that represents rhetorical relationships between the sentence fragments. The discourse tree includes nodes including nonterminal and terminal nodes, each nonterminal node representing a rhetorical relationship between two of the sentence fragments, and each terminal node of the nodes of the discourse tree is associated with one of the sentence fragments. The method matches each fragment that has a verb to a verb signature, thereby creating communicative discourse tree.