IBM: Natural Language Processing and Computer Vision

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/21

encourage image

There's no tags or description

Looks like no tags are added yet.

Last updated 7:52 PM on 5/20/26
Name
Mastery
Learn
Test
Matching
Spaced
Call with Kai

No analytics yet

Send a link to your students to track their progress

22 Terms

1
New cards

Project Debater

is an AI system developed by IBM that can engage in natural language debates with humans. It analyzes vast amounts of data and constructs coherent arguments.

2
New cards

corpus

collection of learned material

3
New cards

tounge-twisters

what simple ideas can turn into due to the complexity of human language

4
New cards

Natural Language Processing (NLP)

is a branch of artificial intelligence focused on enabling computers to understand, interpret, and generate human language.

5
New cards

sentence segmentation

is the process of dividing text into individual sentences. This is crucial for various NLP tasks as it helps in understanding the structure and meaning of written language.

6
New cards

tokens

are individual pieces of text, such as words or phrases, that are used in natural language processing to analyze the structure and meaning of language.

7
New cards

entity

a noun representing a person, place, or thing. It’s not an adjective, verb, or other article of speech.

8
New cards

relationship

a group of two or more entities that have a strong connection to one another.

9
New cards

concept

something implied in a sentence but not actually stated.

10
New cards

Emotion Detection

 identifies distinct human emotion types.

11
New cards

Sentiment analysis

a measure of the strength of an emotion; a means of assessing if data is positive, negative, or neutral

12
New cards

classification problem

a task in machine learning where the goal is to assign categories to inputs based on their attributes.

13
New cards

small data

data that chatbots work with to generate responses or make predictions. Unlike big data, this data is limited in volume but can still provide valuable insights.

14
New cards

classifiers

Algorithms that sort data into predefined categories based on features, enabling tasks such as sentiment analysis and object recognition.

15
New cards

intent

a purpose: the reason why a user is contacting the chatbot.

16
New cards

dialog

a flowchart—an IF / THEN tree structure that illustrates how a machine will respond to user intents

17
New cards

node

a condensed moment of the conservation that contains a statement by the chatbot and a long, expandable list of possible replies.

18
New cards

convolutional neural network (CNN)

process that makes it possible for visual recognition systems to identify things in an image, as in facial recognition. 

19
New cards

generative adversarial network (GAN)

a class of machine learning frameworks where two neural networks contest with each other to generate new data that resembles a given dataset.

20
New cards

AI Debater System Steps

  • Step 1: Learn and understand the topic

  • Step 2: Build a position

  • Step 3: Organize your proof

  • Step 4: Respond to your opponent

21
New cards

Chatbot Frontend

interacts with the person asking questions. It listens (or reads) and speaks (or presents text)

22
New cards

Chatbot Backend

operates application logic and has enough memory to remember earlier parts of a conversation as dialog continues.