Learn Before
Example of Multi-Category Named Entity Recognition
Given the task to identify and classify all named entities from a text, a Multi-Category Named Entity Recognition system can be guided by a prompt such as: 'Identify and classify all named entities in the provided text into categories such as person names, locations, dates, and organizations. List each entity with its type on one line.'
For the input text: 'Is the UK really doing that badly or have travel trends shifted, post-pandemic? For Tom Jenkins, CEO of the European Tourism Organisation, it’s the latter...', the expected output would be:
- Tom Jenkins - Person Name
- European Tourism Organisation - Organization
- UK - Location
- Europe - Location
- 2024 - Date
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Example of Multi-Category Named Entity Recognition
Analyzing Relationships Between Named Entities
A language processing system is configured to perform a specific task: identify all named entities in a text and classify them into one of four categories: PERSON, ORGANIZATION, LOCATION, or DATE. Given the input text: 'On June 5, 2023, the CEO of Innovate Corp, Maria Garcia, announced a new partnership in Paris.' Which of the following outputs correctly represents the result of this task?
Analyzing Named Entity Recognition Output
Evaluating an NER System's Performance
Given the following text, match each identified named entity to its correct category.
Text: 'Dr. Evelyn Reed, a researcher from QuantumLeap Inc., presented her findings in Berlin on October 12, 2023.'
Learn After
A system is tasked with identifying and classifying named entities from the following text: 'For Tom Jenkins, CEO of the European Tourism Organisation, it’s the latter. “I think the UK is doing perfectly well but we’ll see more people going to Europe,” he says of 2024...'. The system produces the output below. Analyze the output and identify the classification error.
System Output:
- Tom Jenkins: Person
- European Tourism Organisation: Organization
- UK: Location
- 2024: Organization
Applying Named Entity Recognition
A system has extracted several named entities from a text about travel trends. Match each extracted entity with its correct category.