Why Word Vectors Make Sense in Natural Language Processing
If you’re up-to-date with progress in natural language processing research, you’ve probably heard of word vectors in word2vec. Word2vec is a neural network configuration that ingests sentences to learn word embeddings, or vectors of continuous numbers representing individual words. The neural network accepts a word, which is first mapped to a one-hot... Read more
An Idiot’s Guide to Word2vec Natural Language Processing
Word2vec is arguably the most famous face of the neural network natural language processing revolution. Word2vec provides direct access to vector representations of words, which can help achieve decent performance across a variety of tasks machines are historically bad at. For a quick examination of how word vectors work,... Read more
Tracking the Progress in Natural Language Processing
This post introduces a resource to track the progress and state-of-the-art across many tasks in NLP. Go directly to the document tracking the progress in NLP. Research in machine learning and in natural language processing (NLP) is moving so fast these days, it is hard to keep up. This... Read more
Sentiment Analysis in R Made Simple
Sentiment analysis is located at the heart of natural language processing, text mining/analytics, and computational linguistics. It refers to any measurement technique by which subjective information is extracted from textual documents. In other words, it extracts the polarity of the expressed sentiment in a range spanning from positive to... Read more
The Art of Building a Chatbot
With the development of deep learning and NLP chatbots become more and more popular. The hype for chatbots is already high and it will be increasing for the next several years. “By 2020, over 50% of medium to large enterprises will have deployed product chatbots” — Van Baker, research vice president... Read more
NLP: Extracting the Main Topics from your Dataset Using LDA in Minutes
I recently started learning about Latent Dirichlet Allocation (LDA) for topic modelling and was amazed at how powerful it can be and at the same time quick to run. Topic Modelling is the task of using unsupervised learning to extract the main topics (represented as a set of words)... Read more
NLP — Building a Question Answering model
I recently completed a course on NLP through Deep Learning (CS224N) at Stanford and loved the experience. Learnt a whole bunch of new things. For my final project I worked on a question answering model built on Stanford Question Answering Dataset (SQuAD). In this blog, I want to cover the... Read more
Using Object Detection for a Smarter Retail Checkout Experience
I have been playing around with the Tensorflow Object Detection API and have been amazed by how powerful these models are. I want to share the performance of the API for some practical use cases. The first use case is a smarter retail checkout experience. This is a hot field right... Read more
A Research-Oriented Look at the Evolution of Word Embedding: Part II
This article is the second article in a two-part series about the evolution of word embedding as told through the context of five research papers. It picks up in midst of the 1990s. To view the first article, click here. A Shift Towards Automatic Feature Generation: Latent Dirichlet Allocation... Read more
A Research-Oriented Look at the Evolution of Word Embedding: Part I
Introduction “You shall know a word by the company it keeps,” insisted John R. Firth, a British linguist who performed pioneering work on collocational theories of semantics. What Firth meant by his 1957 quote was that interrogating the context in which a word is found offers clues to the... Read more