Workdocumentation 2023-12-22

Prompt

I'd like to extract event signatures from a couple of hundred home page texts of scientific events - what would be a prompt for you to get the information in structured format such as yaml or json ? Here is the definition of the event signature: Acronym: A short name for the conference often consisting of 3 to 8 upper case
letters trying to be unique but actually often being ambiguous. For instance, ISWC
may refer to the International Semantic Web Conference or to the International
Symposium on Wearable Computing.
Frequency: Annual, biennial, triennial – most events have an annual frequency, and
this is mostly not stated explicitly (not stated explicitly in this example).
Event reach: Target reach of the conference such as ‘International’, ‘European’, ‘East
Asian’ (International).
Event type: Such as Conference, Workshop, Symposium (Conference).
Year: A two or four-digit reference to the year in which the event took place – not to
be confused with the year of publication of the proceedings, which might be different
(2019).
Ordinal: Often used to enumerate the conference series instances (18th).
Date: Start date and end date or date range of the conference (October 26–30).
Location: Description of the location of the conference often consisting of country,
region, and city – sometimes with details about the exact venue. (Auckland, New
Zealand).
Title: The title often contains scope, type, and subject of the conference (International
Semantic Web Conference).
Subject: Description of what the conference is about often prefixed with ‘on’
(Semantic Web).
Delimiters: A variety of syntactic delimiters such as blanks, commas, colons, brackets
are used depending on the citation style

and an example of a homepage text:
QUATIC'1994
    1st International Conference on the Quality of Information and Communications Technology
    Hotel Penta
    27 May, 1994
    Lisbon, Portugal
    Toggle navigation
    PROCEEDINGS |
    DBLP |
    GOOGLE CITATIONS |
    QUATIC CONFERENCE SERIES
    QUATIC'1994
    Committees
    Program
    Conference Venue
    Sponsors
    QUATIC Conference Series

Answer

To extract event signatures from home page texts of scientific events in a structured format like YAML or JSON, you need to prompt the AI to identify and structure specific pieces of information based on the definition of the event signature you provided. The prompt should guide the AI to look for acronyms, frequencies, event reach, types, years, ordinals, dates, locations, titles, and subjects in the text. Here's how you could formulate such a prompt:

I have texts from home pages of scientific events. I need to extract structured information about each event in a clear, concise format. Here are the details I need for each event signature:

- Acronym: The short name of the conference, often in uppercase.
- Frequency: How often the event occurs, like annual or biennial.
- Event reach: The geographical or demographic reach of the event, like International or European.
- Event type: The format of the event, such as Conference, Workshop, or Symposium.
- Year: The year in which the event takes place.
- Ordinal: The instance number of the event, like 18th or 1st.
- Date: The start and end date or date range of the event.
- Location: The country, region, and city of the event, and sometimes specific venue details.
- Title: The full title of the event, often indicating the scope and subject.
- Subject: The main topic or focus of the event.

Given a homepage text of an event, please identify and extract this information in a structured format (either YAML or JSON). Here's an example of a homepage text:

"QUATIC'1994
1st International Conference on the Quality of Information and Communications Technology
Hotel Penta
27 May, 1994
Lisbon, Portugal
Toggle navigation
PROCEEDINGS |
DBLP |
GOOGLE CITATIONS |
QUATIC CONFERENCE SERIES
QUATIC'1994
Committees
Program
Conference Venue
Sponsors
QUATIC Conference Series"

Based on this text, please extract the event signature information and present it in a structured format.