Lemmatization is one of the most important tasks for text normalization in natural language processing (NLP), i.e. using deep learning to understand text data.

One of the good lemmatizers I found for biomedical domain is BioLemmatizer. However, it is developed in Java and is available from maven repo. I would like to use it from Python, but there seems to be no counterpart for BioLemmatizer in Python. Is there a way I can access BioLemmatizer from Python using some module like JPype. JPype, however, supports access only for the default classes in Java.


1 Answer 1


This area is huge in Python because of machine learning text processing, in fact O'Reilly have an entire book on it . However, we don't really deal with words in Bioinfo SE,

You might want to look at the nltk (natural language toolkit) for Python, but for direct parallels with the Java package bio package (your question) I don't think it's something we would know.

You could solve this via subprocessing into Java, and passing the result back to Python. I get the idea that the core ML/ DL used in natural language is set up for Python. Google for example have fantastic tensorflow stack for this.

  • $\begingroup$ Unfortunately, bio package has many tools dealing with biological sequences, but I require a lemmatizer that work with biomedical literature in English. $\endgroup$
    – PinkBanter
    Commented Jul 21, 2019 at 19:19
  • $\begingroup$ Hi I'm aware of your goals, lemmatization orietated towards biological literature. Its not something we're clued up about, but it's an advanced area of programming $\endgroup$
    – M__
    Commented Jul 21, 2019 at 19:21

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.