Archive of stories published by Explorations in Language and Learning

Homepage

Open in app

All

2017

2018

Desh Raj in Explorations in Language and Learning

Sep 16, 2017

Metrics for NLG evaluation

Simple natural language processing tasks such as sentiment analysis, or even more complex ones like semantic parsing are easy to evaluate since the evaluation simply requires label matching. As such, metrics like F-score (which is the harmonic mean of precision and recall), or even…

Desh Raj in Explorations in Language and Learning

Apr 12, 2018

How to obtain Sentence Vectors?

In several of my previous posts, I have discussed methods for obtaining word embeddings, such as SVD, word2vec, or GloVe. In this post, I will abstract a level higher and talk about 4 different methods that have been proposed to get embeddings for sentences.

1 response

Desh Raj in Explorations in Language and Learning

Jun 15, 2018

Transfer Learning in NLP

Transfer learning is undoubtedly the new (well, relatively anyway) hot thing in deep learning right now. In vision…

1 response

Desh Raj in Explorations in Language and Learning

Sep 28, 2017

Understanding word vectors

This article is a formal representation of my understanding of vector semantics, from course notes and reading reference papers and chapters from Jurafsky’s SLP book. I will be talking about sparse and dense vector semantics, including SVD, skip-gram, and GloVe. In many places, I…

2 responses

Desh Raj in Explorations in Language and Learning

Sep 19, 2017

Trends in Semantic Parsing — Part 1

In this article, I will try to round up some (mostly neural) approaches for semantic parsing and semantic role labeling (SRL). This is not an extensive review of these methods, but just a collection of my notes on reading some recent research on the subject. However…

1 response

Desh Raj in Explorations in Language and Learning

Mar 14, 2018

Online Learning of Word Embeddings

Word vectors have become the building blocks for all natural language processing systems. I have earlier written an overview of popular algorithms for learning word embeddings here. One limitation with all these methods (namely SVD, skip-gram, and GloVe) is that they…

Desh Raj in Explorations in Language and Learning

Apr 23, 2018

An Introduction to Speech Recognition using WFSTs

Until now, all of my blog posts have been about deep learning methods or their application to NLP. Since the last couple of weeks, however, I have started learning about Automatic Speech Recognition (ASR). Therefore, I will also include…

Desh Raj in Explorations in Language and Learning

Dec 6, 2017

Beyond Euclidean embeddings

Representation learning, as the name suggests, seeks to learn representations for structures such as images, videos, words, sentencences, graphs, etc., which may then be used for several objectives. Arguably the most important representations used nowadays are word embeddings…

Desh Raj in Explorations in Language and Learning

Dec 14, 2017

Unsupervised approaches for NMT

Translation is one of those tasks in language where the arrival of deep learning systems, and in particular sequence-to-sequence, has been something like a boon. In less than 4 years since the first paper on Neural Machine Translation, software giants such as Google and…

Desh Raj in Explorations in Language and Learning

Oct 1, 2017

The last 3 years in Text Classification

While working on my undergrad thesis on relation classification of biomedical text using deep learning methods, I quickly hacked together models in Tensorflow that combined convolutional and recurrent layers in various combinations. While some of these…

1 response

These were the top 10 stories published by Explorations in Language and Learning; you can also dive into yearly archives: 2017, 2018.

About

Explorations in Language and Learning

This is a collection of articles on machine learning and deep learning techniques applied to natural language processing. The content includes overviews of popular methods, new approaches for specific NLP tasks, and blogs about the authors’ personal research in the subject.

More information