iKnow and DeepSee. Agenda

Содержание

Слайд 2

Agenda

What is iKnow?
Semantic Analysis.
%iKnow.Queries
Matching Dictionaries.
%iKnow.Semantics.

Newer features:
Attribute Customizations.
iFind.
Text Categorization.
iKnow features in DeepSee.
Configuring iKnow

Agenda What is iKnow? Semantic Analysis. %iKnow.Queries Matching Dictionaries. %iKnow.Semantics. Newer features:
and DeepSee.

Слайд 3

What is iKnow?

iKnow is a semantic analysis tool.
Indexes the concepts and relations

What is iKnow? iKnow is a semantic analysis tool. Indexes the concepts
within text for querying and analysis.
Uses language models rather than training data or ontologies to detect relations.
Supported languages: Dutch, English, French, German, Portuguese, Russian, Spanish, Ukrainian, Swedish*, and Japanese*.
Sources of text include: Plain text files, SQL fields, social media.
*Support added in 2016.1 release.

Слайд 4

Semantic Analysis: Relations, Concepts, Negation

patient

suffered from

acute hypertension

chest pain

but did not mention

Semantic Analysis: Relations, Concepts, Negation patient suffered from acute hypertension chest pain

The patient suffered from acute hypertension but did not mention any chest pain.

Слайд 5

Semantic Analysis Results

Semantic Analysis Results

Слайд 6

Importance of Language Models

iKnow indexing is subject matter neutral.
A language model applies

Importance of Language Models iKnow indexing is subject matter neutral. A language
to any text written in the language: medical, legal, scientific, business, and so on.
iKnow indexing automatically detects meaningful word groups.
Labels “acute hypertension” and “chest pain” as concepts.
Labels “but did not mention chest pain” as a negation context.
No need for ontologies or training data.

Слайд 7

%iKnow.Queries

Includes:
GetTop() – Most frequently occurring entities across a set of sources.
GetRelated()

%iKnow.Queries Includes: GetTop() – Most frequently occurring entities across a set of
– Entities in a relationship with the supplied entity.
GetByEntities() – All CRCs or paths containing a particular set of entities.
GetSummary() – Most relevant sentences in a source.
GetSimilar() – Entities similar to a given entity.

Слайд 8

Matching Dictionary

User provided group of related terms.
Provides external (domain) knowledge to iKnow

Matching Dictionary User provided group of related terms. Provides external (domain) knowledge
results.
Allows for coarser grained analysis.
Example (2001 A Space Odyssey): hal ? hal. hal9000 ? hal. heuristic algorithm computer ? hal.
iKnow smart matching mechanism returns a match score.
Configurable threshold for matches.

Слайд 9

iKnow Architect (2016.1)

Management Portal Tool for creating, configuring, and managing iKnow domains.
Domain

iKnow Architect (2016.1) Management Portal Tool for creating, configuring, and managing iKnow
Settings, Metadata, Data Locations, Blacklists
Compile and build domains.
Launch indexing and knowledge portal pages.
Some iKnow features not supported by Architect. Edit class definition using IDE.
Matching Dictionaries.

Слайд 10

Demonstration

Demonstration

Слайд 11

%iKnow.Semantics (2012.2+)

Introduces concept of dominant entities.
Most important entities not most common.
Algorithm revised

%iKnow.Semantics (2012.2+) Introduces concept of dominant entities. Most important entities not most
for 2015.2 release.
Explained in documentation.
Includes queries:
GetBySource() – Dominant elements in a specific source.
BuildOverlap() – Generates dominant term overlap information for all sources in a domain.
FindMostTypicalSources() – Most typical sources.
FindBreakingSources() – Most atypical sources.

Слайд 12

Attribute Customizations

Negation.
Augment default markers with additional markers for particular use cases.
Sentiment.
No default

Attribute Customizations Negation. Augment default markers with additional markers for particular use
markers.
Supply custom sentiment markers.
Attribute markers.
Supply custom markers in User Dictionary.
iKnow performs attribute tagging during loading.

Слайд 13

iFind

SQL feature for performing text search.
Add iFind index to columns containing text.
Include

iFind SQL feature for performing text search. Add iFind index to columns
iFind index syntax in WHERE clauses of SQL queries.
Support for the following searches:
Stemming and de-compounding.
Word and word phrase search.
iKnow entity search.
iKnow semantic search using path, proximity, and dominance information.

Слайд 14

Text Categorization

Label (categorize) source texts based on their contents (entities and relations).
Create

Text Categorization Label (categorize) source texts based on their contents (entities and
a classifier by analyzing an existing (training) set of already labelled texts
Apply classifier to new and as yet unlabelled texts.
Wizards available for building and testing classifiers.
System Explorer ? iKnow ? Text Categorization

Слайд 15

DeepSee and iKnow

DeepSee cubes can include iKnow indexing results and analyses:
iKnow Dimensions.
Entities

DeepSee and iKnow DeepSee cubes can include iKnow indexing results and analyses:
(concepts and relations).
Dictionary matching results.
Use as rows, columns, and filters on pivot tables just like data and time dimensions.
Detail Listings.
iKnow summaries.
Content Analysis Plugin to allow users to perform a variety of iKnow analyses on text sources.

Слайд 16

Demonstration

Demonstration

Слайд 17

iKnow Dimensions

Entity dimension.
Single level.
Members are entities (concepts or relations).
Analyzer displays first 100

iKnow Dimensions Entity dimension. Single level. Members are entities (concepts or relations).
in decreasing order by spread.
Filter options contain all entities. Searchable.
Dictionary dimension.
Level 1: one member for each dictionary.
Level 2: one member for each item containing all matches for that item.
Matching dictionaries loaded as termlists.

Слайд 18

iKnow Measure

Connects unstructured data to cube.
Purely configuration. Not visible to Analyzer.
Connects DeepSee

iKnow Measure Connects unstructured data to cube. Purely configuration. Not visible to
cube to text sources and dictionaries.
Referenced by iKnow dimensions.

Слайд 19

Content Analysis Plugin

Launch from Analyzer or Dashboard.
Select cell and click
iKnow features

Content Analysis Plugin Launch from Analyzer or Dashboard. Select cell and click
include:
Content Analysis.
Typical and breaking sources.
Entity Analysis.
Overview: frequency and spread for 10 most common groups.
Cell breakdown: distribution of entities selected on Overview tab.
Entities: frequency and spread for entities similar to entity selected on Cell breakdown.

Слайд 20

Demonstration

Demonstration

Слайд 21

Configuring iKnow Measure

iKnow Measure:
Source Values: Property or expression.
Aggregate: Count.
Type: iKnow.
iKnow Source: string,

Configuring iKnow Measure iKnow Measure: Source Values: Property or expression. Aggregate: Count.
stream, file, or domain.
Dictionaries: select from available termlists.

Слайд 22

Configuring iknow Dimensions

Entity Dimension.
Dimension Type: iKnow.
iKnow Type: entity.
iKnow Measure: iKnow measure name.
Dictionary

Configuring iknow Dimensions Entity Dimension. Dimension Type: iKnow. iKnow Type: entity. iKnow
Dimension
Dimension Type: iKnow.
iKnow Type: Dictionary.
iKnow measure: iKnow measure name.

Слайд 23

iKnow Listing Features

Include iKnow summary.
$$$IKSUMMARY[iKnowMeasure, summaryLength].
Include content analysis plugin.
$$IKLINK[iKnowMeasure].
Allows users to see:

iKnow Listing Features Include iKnow summary. $$$IKSUMMARY[iKnowMeasure, summaryLength]. Include content analysis plugin.
summaries, dictionary matches, negation contexts, and dominant entities for selected source(s).

Слайд 24

Suggested Reading

Using iKnow.
Advanced DeepSee Modeling Guide ? Using Unstructured Data in Cubes.

Suggested Reading Using iKnow. Advanced DeepSee Modeling Guide ? Using Unstructured Data in Cubes.
Имя файла: iKnow-and-DeepSee.-Agenda.pptx
Количество просмотров: 39
Количество скачиваний: 0