Changes between Version 13 and Version 14 of Public/WhitePaperChatForOne


Ignore:
Timestamp:
Apr 16, 2023, 12:38:51 AM (20 months ago)
Author:
Boris Horner
Comment:

—

Legend:

Unmodified
Added
Removed
Modified

  • Public/WhitePaperChatForOne

    v13 v14  
    125125
    126126
    127 == Correcting terminology
     127== Terminology correction and extraction
    128128{{{#!div style="background: #DDFFEE; margin: 5px; margin-left: 40%; margin-right: 30px; padding: 5px; border-radius: 10px;"
    129129Here's the text to be corrected:[[br]]
    … …  
    154154It basically performed quite well, but not perfectly well. This is quite characteristic for using the chat. It tends to forget things that were mentioned a while ago and they need to be brought back into consideration by repeating them. When using the API, rule sets can be uploaded which makes the process more reliable. I tested the same text in German before I tried English, and it performed significantly better. I assume, this is due to the way nouns can be composed in German. Apparently, this grammatical property of the German language makes it easier for ChatGPT to recognize terms (and then replace them).
    155155
     156Tests with the extraction of technical terms (and then listing them in alphabetical order, grouped by nouns, verbs and adjectives) were successful in the sense that ChatGPT extracted many words it considered technical terms and sorted them correctly into the categories. However, it seemed to have a rather diffuse "understanding" of what a technical term is. Another problem that can be solved through the API by giving it many examples of text and the contained technical terms to train it.
     157
    156158// By Boris Horner, April 2023//