Skip to content
View bazholifield's full-sized avatar

Block or report bazholifield

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.

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
bazholifield/README.md

Hi! I'm Baz

I'm a computational linguist interested using NLP with real life language use, such as translation, language learning, linguistic analysis, and the ways people actually acquire and produce language. I studied linguistics and computational linguistics at Northwestern, spent a year teaching English in the Basque Country of Spain, and I'm now based in Chicago.

Most of my projects are related to EdTech and NLP. I enjoy building tools to help people learn languages, analyzing various linguistic devices, and studying the benefits and drawbacks of machine translation. I'm particularly drawn to studying tech related to low-resource and linguistically complex languages, aiming to aid language learning, make language tech accessible to more people, and understand how languages differ and affect discourse.

What I'm working on

  • TQE Register - a reference-free machine translation quality estimation process with register awareness, built on XLM-RoBERTa (private, in progress)
  • Polishing and extending existing projects in language learning, error detection, and translation
  • A couple of smaller new projects using AI to aid language learning and analsyis

Stack

Python - PyTorch - TensorFlow - HuggingFace Transformers - scikit-learn - spaCy - NLTK - Flask - FastAPI - Flutter - SQL - R

Languages

Fluent: English, Spanish — Working proficiency: French, German — Basic: Arabic, Basque, Hindi, Mandarin, Japanese

📍 Chicago, IL  ·  LinkedIn

Popular repositories Loading

  1. climate-stance-detection climate-stance-detection Public

    Small-scale replication of Luo et al. (2020) transposed to Twitter with DistilBERT stance classifier, POS analysis, and lexicon comparison across 44k climate change tweets.

    Python

  2. basque-learning-tool basque-learning-tool Public

    Full-stack Basque language learning app: Flutter desktop frontend, FastAPI backend, and Python NLP layer with spaced repetition (SM-2), similarity-based writing evaluation, and an offline Helsinki-…

    Dart

  3. esl-error-detection esl-error-detection Public

    Grammar error detector for ESL learners: a fine-tuned DistilBERT classifier combined with rule-based checks to flag errors, identify the offending word, and explain each mistake in plain English. I…

    Python

  4. spanish-english-transformer spanish-english-transformer Public

    Sequence-to-sequence Transformer for Spanish to English translation, built from scratch in PyTorch with encoder-decoder architecture, SentencePiece BPE tokenizer, beam search decoding, trained on E…

    Jupyter Notebook

  5. spanish-conversation-practice spanish-conversation-practice Public

    Rule-based Spanish conversation simulator with a spaCy NLP pipeline, Google Speech Recognition, and an interactive HTML transcript with per-word definition and conjugation lookup.

    Python

  6. bazholifield bazholifield Public