Skip to content
Avatar
🌳
🌳

Achievements

Achievements

Highlights

  • Pro
Block or Report

Block or report bminixhofer

Block user

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

Report abuse

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

Report abuse
bminixhofer/README.md

Hi, I'm Benjamin! 👋

I'm currently studying Artificial Intelligence at JKU Linz. Previously I worked on Transformers as ML Research Intern at Huawei.

I am especially interested in everything NLP and in Rust as a language for writing fast, correct code.

Some of my projects:

  • nlprule. A fast, low-resource Natural Language Processing and Error Correction library written in Rust.
  • NNSplit. A library implementing a general framework for semantic text segmentation.
  • GerPT2. A small German GPT2 model. I also trained a large version.
  • tractjs. A library for running ONNX and TensorFlow models client-side in the browser. Built on the awesome tract library and accessible from Javascript.

I've also been active on Kaggle some time ago.

Feel free to write me an email at bminixhofer at gmail dot com if you'd like to chat about any of the above (or anything else!).

Pinned

  1. A fast, low-resource Natural Language Processing and Text Correction library written in Rust.

    Rust 333 27

  2. Semantic text segmentation. For sentence boundary detection, compound splitting and more.

    Rust 162 11

  3. German small and large versions of GPT2.

    Python 10

  4. Run ONNX and TensorFlow inference in the browser.

    Rust 51 6

  5. A mostly compliant Rust implementation of the Segmentation Rules eXchange (SRX) 2.0 standard for text segmentation.

    Rust 3 2

900 contributions in the last year

May Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Mon Wed Fri
Activity overview
Contributed to bminixhofer/nlprule, bminixhofer/nnsplit, bminixhofer/tractjs and 5 other repositories

Contribution activity

May 2021

bminixhofer has no activity yet for this period.

April 2021

Created a pull request in bminixhofer/nlprule that received 13 comments

Improve tagger: Return iterators over WordData, remove groups, parallelize deserialization

I had another look at the tagger today. This PR: Changes all the get_tags_* methods to return iterators instead of Vec. Removes the groups. These …

+417 −241 13 comments
1 contribution in private repositories Apr 26

Seeing something unexpected? Take a look at the GitHub profile guide.