Text-analysis agent generating formal model from task description
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F22%3A00365417" target="_blank" >RIV/68407700:21730/22:00365417 - isvavai.cz</a>
Result on the web
<a href="https://www.ciirc.cvut.cz/cs/research-education/projects/nck-kui/sub03/v10/" target="_blank" >https://www.ciirc.cvut.cz/cs/research-education/projects/nck-kui/sub03/v10/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Text-analysis agent generating formal model from task description
Original language description
The outcome of this research is a Natural Language Processing (NLP) algorithm designed to analyze text, particularly users' manuals. The primary objective of the algorithm is to extract step-by-step procedures for setting up, maintaining, and troubleshooting specific devices from the manuals.
Czech name
—
Czech description
—
Classification
Type
R - Software
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/TN01000024" target="_blank" >TN01000024: National Competence Center - Cybernetics and Artificial Intelligence</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Internal product ID
TN01000024/3 - V10
Technical parameters
To achieve this, we employed advanced information retrieval algorithms based on the representation of text chunks. Several different techniques based on embeddings were used to represent these text chunks. To evaluate the Semantic Text Similarity task, we utilized cosine similarity.
Economical parameters
The resulting algorithm is a powerful tool that can effectively analyze and extract information from complex manuals, making it easier for users to understand and follow the step-by-step procedures.
Owner IČO
68407700
Owner name
České vysoké učení technické v Praze, CIIRC