Semantic Word Search
HTML-код
- Опубликовано: 24 окт 2024
- In this video you will learn how to find semantically related words. The video shows how to enter text into Orange and find related words from a predefined list. The video covers Orange widgets for corpus creation, embedding text in vector spaces, and finding nearest neighbors using vector representation.
This video is a part of the Text Mining video series that dives into machine learning, visual analytics, and the joys of interactive analysis of text documents using Orange Data Mining software (orangedatamini...).
The word data set used in this video: file.biolab.si/...
SUBSCRIBE to our channel: / orangedatamining
The development of this video series was supported by grants from the Slovenian Research Agency (including P2-0209, V2-2274, and L2-3170), Slovenia Ministry of Digital Transformation, European Union (including xAIM and ARISA) and Google.org/Tides foundation.
#textmining #machinelearning #orange #visualanalytics #datamining
__
Written by: Blaž Zupan (biolab.si/blaz), Ajda Pretnar Žagar
Presented by: Noah Novšak
Production and edit: Lara Zupan
Intro/outro: Agnieszka Rovšnik
Music by: Damjan Jović - Dravlje Rec
Orange is developed by Biolab at University of Ljubljana (www.biolab.si)
awesome, thanks a lot
Is there a way to install the document embedding widget's underlying model offline instead of it making a connection to an external server? My company's firewall blocks the connection the widget makes to its server.
Not yet, but we are aware of the issue. We're just short on text add-on developers, so we're unsure when we can add it.
why cosine?
Cosine is used for computing similarity on complex data, such as text. Of course, there's also a longer, more mathematical explanation. :D