Laser Encoder: Sentiment Analysis

Overview

In this tutorial, we'll explore the power of Language-Agnostic SEntence Representations (LASER) for generating multilingual embeddings. We'll then use these embeddings to perform clustering on the MASSIVE dataset. Our goal was to show that LASER embeddings can effectively group texts not only by their semantic content but also across different languages. LASER can encode sentences from multiple languages into a shared embedding space, allowing for cross-lingual understanding and comparison. We'll see how this capability is useful for tasks like multilingual embeddings clustering.

Getting Started

To run the notebook in Google Colab, simply click the "Open in Colab" button below:

Simple interactive Demo

To better understand this tutorial, you can checkout this interactive demo hosted on huggingface spaces.