Embedding

Introduction There are some questions that everyone has asked themselves at least once in their life: “what is the meaning of life?”, “what happens after you die?” and of course: “what is the purpose of sentence embeddings?”. Or is it just me? Jokes aside, sentence embeddings can be a bit of…

A guide on how to implement word2vec using PyTorch — 1. Introduction The concept of word embeddings, i.e., the ability to capture semantic and syntactic meaning using vectors, is set to revolutionize deep natural language processing (NLP). Even though word embeddings as a concept was first introduced by Bengio et al [1] in 2003, Mikolov et al’s work on Word2Vec algorithm [2]…

Needless to say, transformers are famous solutions now, even for vision(Image classification) and document layout analysis(for eg. extracting information from receipt documents) tasks. I was slightly skeptical wrt using transformers for document layout analysis since the task is highly dependent on the positioning of the objects. To test the efficacy…

A quick guide to understanding embeddings, including real world applications and how to compute them — Written in collaboration with Francisco Castillo Carrasco, data scientist at Arize AI. Imagine you are an engineer at a promising chatbot startup dedicated to helping people find the medical care they need quickly. You have millions of chat interactions between customers and medical personnel. You’re building a…

If there is one thing I’ve been obsessed about as a researcher, this would be knowledge representation, or the art of converting the information we have about the real world into something a computer can manage (and even “understand”). Knowledge expressed as a set of numbers, arranged in a particular…

Udacity You can find the Github repository related to this blog here. Introduction Starbucks provides simulated data that mimics customer behavior on the Starbucks rewards mobile app. Once every few days, Starbucks sends out an offer to users of the mobile app. An offer can be merely an advertisement for a drink…

Extract topics by clustering contextual sentence embeddings — TL;DR We conduct extensive experiments comparing clustering-based topic models and conventional neural topic models (NTMs), showing an alternative way to extract topics from documents. Check out our NAACL 2022 paper 📄 “Is Neural Topic Modelling Better than Clustering? …

In early February, we were in the process of developing our application, BookMapp. Just as a background, the principal value proposition of the app is to identify similarities across the uploaded set of multiple books. In other words, we are creating an n-dimensional (where n is the number of books…

The black box technique allows many of us to run a few instances of machine learning models as a beginning machine learning modeller before realising that the field is far too big and necessitates a significant time commitment and amount of work on our part. Initially, the datasets that would…