Blogs on embedding vectors » Lamarr Institute

00 Blog Brito Automatische Kategorisierung neu - Lamarr Institute for Machine Learning (ML) and Artificial Intelligence (AI)

Automatic categorization of online store items from product descriptions

16. November 2022

In this blog post, author Eduardo Brito shows how the classification of items in online stores can be automated and presents a resource-saving solution using an application example....

00 Blog Hillbrand Biesner - Lamarr Institute for Machine Learning (ML) and Artificial Intelligence (AI)

Research

Interpreting word representations and topic analysis using matrix factorization

14. April 2021

Word embeddings form the basic building block for the algorithmic analysis and processing of texts, such as text classification, translation, and text generation. Interpretable vector representations of words encode semantic relationships in an understandable way and enable the analysis of cross-word topics....

Research

BERT: How Do Vectors Accurately Describe the Meaning of Words?

12. March 2021

BERT makes it possible to solve many problems of natural language interpretation. This article explains in detail the architecture, properties and functionality of the model developed by Google....

Basics

Capturing the meaning of words through vectors

10. March 2021

The meaning of words can be represented by numerical vectors that also include the neighboring words. This allows syntactic and semantic relationships of the language to be captured and used to interpret meanings....

Automatisierte Stichwortvergabe für kurze Texte: Semantische Similarities of automatically extracted key terms from patent abstracts in the field of laser technology|||

Application

Automated Keyword Assignment for Short Texts

13. January 2021

In order to enable a targeted search in extensive text collections, it is common to assign keywords. We describe methods for automatically assigning content-related keywords to short texts....