Applications

To illustrate the use of PySeqLab package, we give examples from multiple domains:

Natural language processing (NLP)

Chunker

We show how to build and train a chunker using CoNLL 2000 dataset in this tutorial. Moreover, the project repository is available on bitbucket.

Part-of-Speech tagger

Similarly, we demonstrate how to train a part-of-speech tagger using GENIA corpus 3.02 part of speech annotation in this tutorial. The project repository is available on bitbucket.

Bio-named entity recognizer

We conclude the NLP examples by this tutorial on training a biomedical named entity recognizer (BioNER) using BioNLP/NLPBA 2004 dataset. The project repository is available on bitbucket.

Eukaryotic splice-junction sequences predictor

We demonstrate how to train a splice-junction classifier using Molecular Biology (Splice-junction Gene Sequences) Data Set in this tutorial. Moreover, the project repository is available on bitbucket.

Human activity recognition (HAR) classifiers

We demonstrate how to train a modes of locomotion classifier and gestures movements classifier using the OPPORTUNITY activity recognition dataset in this tutorial. Moreover, the project repository is available on bitbucket.