Topic 4 - Dialogflow

Question 1

Turing Test

Answer 1

A test proposed by Alan Turing to determine if a computer can exhibit -intelligent behavior equivalent to, or indistinguishable from, that of a human.

Question 2

ELIZA

Answer 2

An early chatbot developed by Joseph Weizenbaum, known for using simple pattern matching to simulate conversation.

Question 3

Chinese Room Argument

Answer 3

A philosophical thought experiment by John Searle arguing that symbol manipulation alone does not constitute genuine understanding.

Question 4

Winograd Schemas

Answer 4

A type of test using sentences with ambiguous pronoun references that require common-sense reasoning to resolve, used as an alternative to the Turing Test.

Question 5

LAMBADA

Answer 5

A benchmark test designed to evaluate the ability of language models to account for discourse aspects and long-range dependencies.

Question 6

The Wozniak “coffee test”

Answer 6

Evaluate an AI’s ability in practical problem-solving in a real-world environment or setting

Question 7

Goertzel Tests

Answer 7

1. Story understanding
2. Passing the elementary school reading curriculum
3. Graduating (virtual-world or robotic) preschool

Question 8

Agent

Answer 8

A virtual entity in Dialogflow that handles conversations with end-users using natural language understanding.

Question 9

Intent

Answer 9

In Dialogflow, an intent represents an end-user’s intention for a conversation turn, mapping user input to a specific action the agent should take.

Question 10

Entity

Answer 10

In Dialogflow, an entity dictates how specific data points (like dates, numbers, or names) are extracted from user expressions.

Question 11

Annotation

Answer 11

The process of marking parts of training phrases in Dialogflow to configure associated parameters for data extraction.

Question 12

Training Phrases

Answer 12

Example phrases provided to a Dialogflow agent to help its machine learning model understand how to match user expressions to intents.

Question 13

Actions

Answer 13

You can define an action for each intent. When an intent is matched, Dialogflow provides the action to your system, and you can use the action to trigger certain actions
defined in your system.

Question 14

Parameters

Answer 14

Values extracted from an end-user expression when an intent is matched, often used to collect specific information needed for an action.

Question 15

Responses

Answer 15

You define text, speech, or visual responses to return to the end-user. These may provide the end-user with answers, ask the end-user for more information, or terminate the conversation

Question 16

Context

Answer 16

In Dialogflow, contexts are similar to natural language context, used to control the flow of conversation by influencing intent matching based on the current conversational state.

Question 17

Events

Answer 17

With events, you can invoke an intent based on something that has happened, instead of what an end-user communicates. Example: Default Welcome Intent.

Question 18

Slot Filling

Answer 18

The process in Dialogflow where the agent collects all required parameter data from the end-user until all necessary information for an intent is provided.

Question 19

Fulfillment

Answer 19

A feature in Dialogflow that allows an agent to send information about a matched intent to an external webhook service for dynamic processing and response generation.

Question 20

Webhook

Answer 20

A mechanism used in Dialogflow fulfillment to send information about a matched intent to an external service via an HTTP POST request.

Question 21

NLU (Natural Language Understanding)

Answer 21

The ability of a computer program to understand human language in its written or spoken form.

Question 22

Dialogflow Console

Answer 22

A web user interface provided by Dialogflow for creating, building, and testing agents.

Question 23

Weak AI

Answer 23

The goal of building AI programs that can demonstrate intelligent behavior and capabilities without claiming to possess genuine understanding or consciousness.

Question 24

Strong AI

Answer 24

The theoretical goal of building AI programs that genuinely possess human-like understanding, consciousness, and cognitive abilities.

Question 25

System Entity

Answer 25

Pre-built entity types provided by Dialogflow (e.g., @sys.date, @sys.number) for common data types.

Question 26

Output context

Answer 26

Controls active contexts. When an intent is matched, any configured output contexts for that intent become active.

Question 27

Input context

Answer 27

Controls intent matching. While contexts are active, Dialogflow is more likely to match intents that are configured with input contexts that are a subset of currently active contexts.