Expert.ai

Question 1

Morphology

Answer 1

In linguistics, morphology (/mɔːrˈfɒlədʒi/[1]) is the study of words, how they are formed, and their relationship to other words in the same language.[2][3] It analyzes the structure of words and parts of words such as stems, root words, prefixes, and suffixes. Morphology also looks at parts of speech, intonation and stress, and the ways context can change a word’s pronunciation and meaning.

Question 2

Semantics

Answer 2

Semantics (from Ancient Greek: σημαντικός sēmantikós, “significant”)[a][1] is the study of meaning, reference, or truth. The term can be used to refer to subfields of several distinct disciplines, including philosophy, linguistics and computer science.

Question 3

Cogito Studio

Answer 3

Anintegrated development environment for building and deploying a custom AI-based text model that leverages the cognitive abilities of the expert.ai platform. •The command center for expert.ai-powere

Question 4

Natural Language Processing (NLP)i

Answer 4

Natural Language Processing (NLP)is a field of Artificial Intelligence (AI) concerned with programming computers to analyze human language.
NLP is a combination of:•Linguistics (the study of grammar)•Computer scienceNLP is the application of linguistic grammar in computer programming with the goal of achieving AI capable of processing natural language.

Question 5

Syntax

Answer 5

In linguistics, syntax is the set of rules, principles, and processes that govern the structure of sentences (sentence structure) in a given language, usually including word order. The term syntax is also used to refer to the study of such principles and processes.[3] The goal of many syntacticians is to discover the syntactic rules common to all languages.

Question 6

Dependency Parsing

Answer 6

In dependency parsing, there are no phrases or sub-phrases. Instead, dependency parses focus on individual words and their direct relations to each other, even when the words are far apart

Question 7

Constituency parsing

Answer 7

Constituency parsing produces a tree that encodes the internal structure of the sentence and its phrases.

Question 8

What is NLU

Answer 8

Natural Language understanding (NLU) is the branch of NLP that employs semantics to get machines to understand text.

Question 9

Semantics

Answer 9

Semantics uses the context (combined with syntactic information) to determine the proper meaning of words even when are ambiguous.

Question 10

Expert Ai’s Knowledge graph

Answer 10

A knowledge base: a crowded collection of interconnected concepts.
A graph: concepts are organically set up in branches with connections to other concepts based on their meaning.
A lexical database: each concept/syncon has linguistic properties including the synonyms that can be used to refer to the concept (i.e. lemmas).

Question 11

NLP Algorithm use cases

Answer 11

TEXT CLASSIFICATION(or CATEGORIZATION)
DATA MINING(or EXTRACTION).

Question 12

Classification

Answer 12

Classification is the automatic application of predefined categories or tags to text.

Question 13

Data Mining

Answer 13

Data Mining is the process of automatically collecting data

Question 14

Symbolic approach

Answer 14

This approach involves designing hand-built linguistic rules to apply to text. Rules follow a very simple criteria:IF linguistic condition THENproduce an outcome

Question 15

Knowledge Engineering

Answer 15

Knowledge Engineering encloses all processes behind the design and development of every single component of a cognitive computing model built with expert.ai to assist with issues related to a specific programmed field of knowledge.

Question 16

Cogito Studio

Answer 16

Cogito Studio provides an integrated environment for text analytics project modelling, knowledge enrichment and data mining results evaluation, allowing customers to speed up the deployment of their projects with both symbolic and machine learning techniques.

Question 17

Cogito Discover

Answer 17

Cogito Discover is the production platform where you install the LPK and integrate it with the customer’s environm

Question 18

TAXONOMY

Answer 18

Taxonomies provide machines ordered representations. According to Bowles, a Taxonomy represents the formal structure of classes or types of objects within a domain. Bowles noted that taxonomies:

Follow a hierarchic format and provides names for each object in relation to other objects.
May also capture the membership properties of each object in relation to other objects.
Have specific rules used to classify or categorize any object in a domain. These rules must be complete, consistent and unambiguous
Apply rigor in specification, ensuring any newly discovered object must fit into one and only one category or object
Inherits all the properties of the class above it, but can also have additional properties.

Question 19

Taxonomy

Answer 19

investigate your texts and identify their core topics.These topics can be organized into a tree structure, with more generic categories breaking down into more specific categories.The result is called a TAXONOMY.

Question 20

Ontology

Answer 20

a subset of Taxonomy, but with more information about the behavior of the entities and the relationships between them. Bowles defined an Ontology as a domain: “including formal names, definitions and attributes of entities within a domain.”

Question 21

taxonomy

Answer 21

It’s a breakdown structure of multiple topics set up in a logical arrangement defining a subject.

Question 22

Classification

Answer 22

Automatic classification of documents assigning them to one or several categories belonging to a taxonomy.

Question 23

Data mining

Answer 23

Data mining is the process of automatically extracting structured information from unstructured and/or semi-structured texts.
Automatic identification of elements and terms in a text which are then placed into classes.

Question 24

Extraction classes

Answer 24

Extraction classes can be thought of as a small ontology. They are like tables for storing your results.

Question 25

Extraction classes

Answer 25

Extraction classes are containers that identify the types of terms that have been extracted. The terms in one class must have some property or attribute in common that differentiates them from other classes by kind, type, domain, etc.

Question 26

Cogito Studio Analytics

Answer 26

Get your Knowledge Base in depth by making full use of the OOTB analysis tools and semantic processing•Greater search granularity, which is achieved through search tools and additional search functionalities•It allows to perform searches on all library and analysis documents•Explore huge libraries and get all kind of information regarding their content in short time and in a clear, effective, user-friendly GUI•It helps you during the initial analysis of your Knowledge Base, but also during the development phase.

Question 27

Project Editor

Answer 27

In Project Editor it is possible to develop your algorithms, validate them on a text document and access the whole Cogito Studio tool suite

Dashboard showing project sources and configurationsAllows for •Developing, compiling and testing Categorization and Extraction rules to shape your algorithms making use of the Semantic Analysis and leveraging the project Sensigrafo•Validating categorization and/or extraction results on text documents•Accessing the whole expert.ai tools suite from the GUI

Question 28

Project Panel

Answer 28

Project Panel:
Lists the source files belonging to the project sorted in a tree structure according to the respective algorithm (Categorization and Extraction)

Question 29

The Semantic Analysis panel

Answer 29

The Semantic Analysis panel displays the grammatical and semantic analysis of the input text•

Question 30

Rule Editor

Answer 30

Rule Editor

Is an advanced text editor for viewing and editing rules file sources and configurations

Question 31

View Menu•

Answer 31

View Menu•Allows for managing panels and toolbars

Question 32

Entities & Tags Panel

Answer 32

Entities & Tags Panel•Provides a list of entities that Cogito Studio is able to identify and provide out-of-the-box as useable data

Question 33

Relevant Information Panel

Answer 33

Relevant Information Panel:

Provides the main and most relevant elements automatically identified by the Semantic Disambiguator in the analyzed text

Question 34

CATEGORIZATION and EXTRACTION RESULTS panels

Answer 34

The CATEGORIZATION and EXTRACTION RESULTS panels•Show the results of categorization and extraction and highlight them in the text

Question 35

The Taxonomy panel

Answer 35

The Taxonomy panel is key to categorization as it displays the project taxonomy (the categories tree) and its structure

Question 36

The Templates panel

Answer 36

The Templates panel is key to extraction as it displays the project extraction classes and their organization