Comparisons

How can you improve search relevance? Does a dictionary stemmer perform better than an algorithmic one? What about embeddings and deep learning models? We try to answer these questions by measuring and comparing approaches with several evaluation data sets.

Experiments

You want to run your own evaluation from start to finish? How do you prepare the data sets, configure your search engine and run the evaluation? You can follow our example experiments step by step and run the code with our provided Google Colab notebooks.

Guides

You want to dive deeper into the used datasets, algorithms and search engines? Here you can find in-depth guides about the techniques and tools we use, as well as interesting topics and new developments. You can start by reading about pragmatics in general.