Yves Peirsman bio photo

Yves Peirsman

Crazy about Natural Language Processing.

Twitter LinkedIn

Yves Peirsman's blog

2017

Understanding Deep Learning Models in NLP

Deep learning methods have taken Artificial Intelligence by storm. As their dominance grows, one inconvenient truth i...

2016

DIY methods for sentiment analysis

In my previous blog post, I explored the wide variety of off-the-shelf solutions that are available for sentiment ana...

Off-the-shelf methods for sentiment analysis

Sentiment analysis is one of the most popular applications of Natural Language Processing. Many companies run softwar...

Text Classification Made Simple  

When you need to tackle an NLP task — say, text classification or sentiment analysis — the sheer number o...

NLP in the Cloud: Measuring the Quality of NLP APIs

Natural Language Processing seems to have become somewhat of a commodity in recent years. More than a few companies h...

NLP People: the 2016 NLP job market analysis

When the University of Leuven asked me to give a guest lecture in their Master of Artificial Intelligence earlier thi...

2015

Generating Genre Fiction with Deep Learning

These days Deep Learning is everywhere. Neural networks are used for just about every task in Natural Language Proce...

Text Retrieval & Search Engines (Coursera): Week 4 Part 2: Recommender Systems

Last month I took the online course Text Retrieval & Search Engines on Coursera, and I’m using this blog to write...

Visualizing Word Embeddings with t-SNE

When you work with high-dimensional datasets such as the word embeddings produced by word2vec or GloVe, it’s importan...

Text Retrieval & Search Engines (Coursera): Week 4 Part 1: Web Search

Last month I took the online course Text Retrieval & Search Engines on Coursera, and I’m using this blog to write...

NLP Meets Linguistics: Detecting Synonyms in Pluricentric Languages

The most recent issue of the International Journal of Corpus Linguistics features an article on word variation by my ...

Text Retrieval & Search Engines (Coursera): Week 3 Part 2: User Feedback

This month I’m taking the online course Text Retrieval & Search Engines on Coursera, and I’m using this blog to w...

Text Retrieval & Search Engines (Coursera): Week 3 Part 1: Query Likelihood Model

This month I’m taking the online course Text Retrieval & Search Engines on Coursera, and I’m using this blog to w...

Text Retrieval & Search Engines (Coursera): Week 2

This month I’m taking the online course Text Retrieval & Search Engines on Coursera, and I’m using this blog to w...

Text Retrieval & Search Engines (Coursera): Week 1

Last week, Text Retrieval & Search Engines by the University of Illinois kicked off on Coursera. I’ve signed up t...

Book review: The Signal and the Noise by Nate Silver

I recently read Nate Silver’s The Signal and the Noise, a book about statistical prediction. Silver is famous for bui...

Notable NLP: GloVe — Global Vectors for Word Representations

In NLP research, models of word meaning are making a comeback. While previously, attention seemed to shift from words...

2014

NLP Classics (1): Automatic Retrieval and Clustering of Similar Words

In this series of blog posts, I present some of the most influential papers from the recent history of Natural Langua...

Through Good Times and Bad Times: Measuring the Happiest and Saddest Episodes of Friends

This September 20 years ago, the first episode of Friends aired on NBC. The sitcom became a world-wide success, and e...

Taaltechnologie bewijst: OpenVld had de kleinste invloed op het Vlaamse regeerakkoord

Taaltechnologie is straf spul. Ze kan pedofielen ontmaskeren op het internet, of J.K. Rowling aanwijzen als de auteur...

Hoe moeilijk is het Vlaamse regeerakkoord?

De publicatie van het Vlaamse regeerakkoord eerder deze week maakte heel wat reacties los, niet enkel op politiek, ma...