Automated Specialized Dictionary Generation via Phrase Clustering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional dictionaries often fail to include specialized phrases specific to particular contexts or domains, such as fictional or domain-specific terms, due to their fragmented and non-comprehensive nature, making them unsuitable for automated processing.

Innovation Solution

A computer-implemented method for automatically generating specialized dictionaries by extracting potential phrases from a document corpus, clustering them, selecting representative phrases, extracting definitions, and storing them for association with their meanings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional manual dictionary creation methods are used, then dictionaries can be created with standard words and phrases, but they fail to include specialized phrases specific to particular contexts or domains

Engineering Contradiction:
Improvecoverage of specialized phrasesVSAvoidmanual creation effort
Core Design Contradiction:
Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The system enables dictionaries to create themselves automatically by extracting phrases from document corpora, clustering them by similarity, and selecting representative phrases as dictionary entries without requiring manual curation for each specialized domain

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system changes the approach from static manual compilation to dynamic automated generation by adjusting parameters such as phrase extraction thresholds, clustering algorithms, and selection criteria to adapt to different domains and contexts

Inventive Principle:
Principle #35Parameter changes

2Reliability

If conventional dictionaries are used, then they provide standard language coverage, but they are fragmented and non-comprehensive for automated processing

Engineering Contradiction:
Improvecomprehensiveness for automated processingVSAvoiddictionary structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the dictionary creation process into distinct automated stages: phrase extraction from corpora, clustering by semantic similarity, representative phrase selection, and definition generation, making the complex task manageable and reliable

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system creates a universal dictionary generation framework that can handle multiple domains and specialized contexts through automated phrase extraction and clustering, making the dictionary comprehensive and suitable for various automated processing tasks

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Adaptability or versatility

If manual efforts are made to create fragmented dictionaries, then certain specialized phrases may be included, but the techniques are not suitable for all domains

Engineering Contradiction:
Improvedomain-specific coverageVSAvoiddictionary creation efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system automatically adapts to different domains by extracting phrases from domain-specific document corpora and generating specialized dictionaries without requiring manual intervention for each domain, greatly improving productivity

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system dynamically adjusts to different domains by changing the input corpus and applying consistent automated processes, enabling versatile domain-specific dictionary creation while maintaining high productivity through automation

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS9483460B2Automated formation of specialized dictionaries
Publication Date: 2016.11.01 GOOGLE LLC
  • US9483460B2 patent drawing
  • US9483460B2 patent drawing
  • US9483460B2 patent drawing

AI summary

A document analysis system analyzes a corpus of documents and automatically generates a dictionary of specialized phrases not already in conventional dictionaries. The dictionary generation process involves a series of operations on the phrases to identify the phrases most suitable for inclusion in a dictionary, such as phrase scoring and phrase clustering. The dictionary generation process also comprises the identification of one or more corresponding definitions for the various phrases identified for inclusion in the specialized dictionary.