Elsevier still looking for papers on Creative Language Processing

Elsevier is going to publish a special issue dedicated only to creative language processing. Should submit papers only researchers working on innovative and different ways of doing Natural Language Processing (NLP). Papers about classic Computer Linguistics (CL) and NLP methods won’t be accepted. The goal here is focus more on humor, deceptive language and figurative […]

Build graphs using text

Yesterday, we transformed a normal dataset into a graph. Today, let’s do the same thing, but using a text document. Reuse the article “Python NLP Tutorial: Building A Knowledge Graph using Python and SpaCy” written by Marius Borcan, to do it, but do a few changes: Look for an article in your language. Describe what’s […]

Build Graphs using your dataset

For the last days, we have been working into building our own dataset. Today, is time to do something interesting with it and transforming it into a graph. Graphs are a great ways to discover relationships, but not every data can be represented in this way. Imagine that you have an e-commerce site with thousands […]

Read about ontologies

A few days ago, we started to build a dataset. Before yesterday, we also saw how to gather data using microdata. Today, we will learn about ontologies. So, today’s task is simple and complicated at the same time. Learning abou what’s an ontology and how benefitial it can be for machine learning is too much […]

Create datasets using semantic web

Now you know what the semantic web is, you must be asking yourself how this is important for a machine learning practitioner. Semantic annotated pages may provide you quick and normalized information, without the need of creating complex scraping bots and more complex yet processing code. Imagine that you have to scrape an e-commerce website. […]

Read about semantic web

Semantic web is one of the most ambitious internet projects. But it is definitely a game changer. When we talk about semantic web, we are actually referring to concepts like linked data, knowledge graphs, RDF and abstract concepts representation that may help computers to understand human knowledge (but it’s not only all of that). Linked […]

Explore the dataset you created

Today’s challenge is a continuation of yesterday’s task. If you have created a database, even if it is small, today will be the time to explore it. Again, since every project is different and you may choose to build a dataset of basically anything, there’s no notebook to share today 🙁 From my side, I […]

Create a dataset

Today’s challenge is about creating your own dataset. I have already discussed how important is to understand this topic: since a lot of introductory Machine Learning examples use toy datasets, we don’t always have the opportunity to understand the issues of creating our own dataset. Since every project is different and you may choose to […]

NLP – Fetch data using rss feeds

Getting data for textual analysis should not be limited to scrapping websites. There are many ways to get valuable information from websites, like fetching data from rss feeds. But rss is not that easy to find anymore. Mostly because, well… who reads it? I do… I still use solutions like Feedly to ready articles, but […]

Clustering text to find different themes

Today’s problem is a continuation of yesterday’s. Yesterday, I used Gensim to create a summary of some internet articles in order to create a business plan. However, sometimes you can come up with a lot of text. Some of they will make sense and some others will be garbage. I thought I could use clustering […]