Proximity-Based Candidate Answer Pre-Processor for QA Systems

Solution Overview

Problem

Current cognitive systems, such as QA systems, face inefficiencies in processing natural language input, leading to high time and resource expenditure in generating answers, especially when dealing with large sets of candidate answers.

Innovation Solution

Implementing a proximity-based candidate answer pre-processor engine that identifies a subset of candidate answers within a predetermined proximity of anchor entities in an ontology data structure, reducing the number of answers to be evaluated and focusing on those with close relationships to the input question.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a QA system evaluates all candidate answers from a large corpus, then answer accuracy is improved, but processing time and resource consumption increase significantly

Engineering Contradiction:

Improveanswer accuracyVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary filtering of candidate answers by evaluating their proximity to anchor entities in the ontology before full QA processing. This pre-processing step identifies and eliminates unlikely candidates early, so that only promising candidates undergo complete evaluation, reducing overall processing time while preserving accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The invention extracts and evaluates specific features of candidate answers - namely their semantic proximity to anchor entities in the ontology. By focusing only on this particular feature for initial filtering, the system can rapidly eliminate large numbers of irrelevant candidates without performing full QA analysis on each one.

Inventive Principle:

Principle #2Taking out (Extraction)

2Reliability

If a QA system evaluates all candidate answers from a large corpus, then answer accuracy is improved, but resource consumption increases significantly

Engineering Contradiction:

Improveanswer accuracyVSAvoidresource consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary filtering of candidate answers by evaluating their proximity to anchor entities in the ontology before full QA processing. This pre-processing step identifies and eliminates unlikely candidates early, so that only promising candidates undergo complete evaluation, reducing overall resource consumption while preserving accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The invention extracts and evaluates specific features of candidate answers - namely their semantic proximity to anchor entities in the ontology. By focusing only on this particular feature for initial filtering, the system can rapidly eliminate large numbers of irrelevant candidates without performing full QA analysis on each one, thereby reducing computational resource consumption.

Inventive Principle:

Principle #2Taking out (Extraction)

3Productivity

If the system uses ontology proximity filtering to reduce candidate answers, then processing efficiency is improved, but the complexity of the system increases

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system introduces an intermediary component - the proximity evaluation module that operates between candidate answer generation and full QA processing. This module uses the existing ontology structure as a mediator to filter candidates, adding functionality without requiring complete system redesign and maintaining relatively simple integration with existing QA components.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11651279B2LAT based answer generation using anchor entities and proximity

Publication Date: 2023.05.16 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Mechanisms are provided for implementing a proximity based candidate answer pre-processor engine that outputs a sub-set of candidate answers to a question and answer (QA) system. The mechanisms receive a lexical answer type (LAT) and an entity specified in an input natural language question as well as an ontology data structure representing a corpus of natural language content. The mechanisms identify a set of candidate answers having associated nodes in the ontology data structure that are within a predetermined proximity of a node corresponding to the entity, and a sub-set of candidate answers in the set of candidate answers having an entity type corresponding to the LAT. The mechanisms output, to the QA system, the sub-set of candidate answers as candidate answers to the input natural language question for evaluation and selection of a final answer to the input natural language question.