Monthly Archives: May 2017

You are browsing the site archives by month.

Lemmatization of German language text

Lemmatization is the process of finding the base (or dictionary) form of a possibly inflected word — its lemma. It is similar to stemming, which tries to find the “root stem” of a word, but such a root stem is often not a lexicographically correct word, i.e. a word that can be found in dictionaries. A lemma is always a lexicographically correct word.

When using text mining models that depend on term frequency, such as Bag of Words or tf-idf, accurate lemmatization is often crucial, because you might not want to count the occurrences of the terms “book”, and “books” separately; you might want to reduce “books” to its lemma “book” so that it is included in the term frequency of “book”.

For English, automatic lemmatization is supported in many Python packages, for example in NLTK (via WordNetLemmatizer) or spaCy. For German, however, I could only find the CLiPS pattern package which has limited use (e.g. it cannot handle declined nouns) and is not supported in Python 3. By using the annotated TIGER corpus of the University of Stuttgart, I will try to measure the accuracy of a lemmatizer based on the pattern.de module and will suggest an improved lemmatizer which improves pattern.de’s accuracy by about 10%.

Read More →

Interactive Balloon Charts with d3-balloon

As explained before, balloon plots can be a good way to compare many observations with lots of variables. I have now created a small extension for d3.js v4 that allows to implement interactive balloon charts quite easily. It is available on GitHub and can be seen live in action for a recent news article about segregation in schools on the WZB website.

Read More →

Linkdump #41

R
Python
Interesting articles, projects and news

Linkdump #40

R
Python
Interesting articles, projects and news

Linkdump #39

R
Python
Interesting articles, projects and news