Skip to content
View phillijm's full-sized avatar
🏳️‍🌈
🏳️‍🌈
1 follower · 2 following

Block or report phillijm

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
phillijm/README.md

Hi there, I'm Jesse! 👋

Computer Science PhD candidate at Lancaster University.

My research interests include Source Code Summarisation, Natural Language Processing, and Software Engineering.

My PhD, "The Automated Generation of Source Code Summaries Using Natural Language Processing Techniques" focuses on using Large Language Models, and other NLP techniques to automatically summarise source code methods.

Publications

Get in touch

LinkedIn | Website | Main GitHub Account | Google Scholar

Pinned Loading

  1. CodeSumBARTCodeSumBARTPublic

    Replication package for "Metric-Oriented Pretraining of Neural Source Code Summarisation Transformers to Enable more Secure Software Development".

    Python

  2. TransformerAssistedLLMCodeSumTransformerAssistedLLMCodeSumPublic

    Replication package for "Transformer-Assisted LLM-Based Source Code Summarisation: to Enable More Secure Software Development", presented at NLPAICS 2026

    Python

  3. HowDoesBERTScoreWorkHowDoesBERTScoreWorkPublic

    How Does BERTScore Work? A quick (and slightly inaccurate) overview.

    Jupyter Notebook

  4. JavaDatasetCleanerJavaDatasetCleanerPublic

    Prepare the Funcom Filtered dataset of Java method-comment pairs for neural source code summarisation using NeuralCodeSum.

    Java

  5. This code contains an additional met...This code contains an additional method which should be added to the JavaDatasetPreprocessor class in the replication package found at: https://github.com/phillijm/JavaDatasetCleaner. This update is used in Chapter Six of my Thesis.
    1
    publicclassJavaDatasetPreprocessor
    2
    {
    3
    /**
    4
     * Re-tokenises summaries.
    5
     **/
  6. Python Script to calculate Cohen's d...Python Script to calculate Cohen's d (https://en.wikiversity.org/wiki/Cohen%27s_d).
    1
    defgetCohensD(a: list, b: list) ->float:
    2
    """ Run Cohen's d, the effect size of two lists.
    3
     Args:
    4
     a (list(float)): the first list of data.
    5
     b (list(float)): the second list.