Question Answering with BERT on Azure

A fine-tuned BERT QA system, benchmarked against classical baselines and deployed for real-time inference on Azure ML.

Python · BERT · Hugging Face · Azure ML · SQuAD

benchmarkSQuADfine-tuneBERT · HFbaselinesTF-IDF · Jaccardsimilarity scoringembeddingsAzure MLendpointanswerreal-time
architecture

Matching a user's question to the sentence that actually answers it is deceptively hard. Lexical overlap fails on paraphrase, and deep models are easy to demo but hard to serve with acceptable latency.

I fine-tuned a BERT-based question-answering system on SQuAD to match queries against candidate answer sentences, using semantic similarity over sentence embeddings, and benchmarked it against Jaccard and TF-IDF baselines to prove the deep model earned its cost. The model was deployed on Azure Machine Learning with a scoring pipeline optimized for both latency and accuracy.

Full-stack ML deployment, demonstrated end to end: fine-tuning, packaging, serving, and real-time inference. The baseline-comparison discipline, measure the simple thing before shipping the complex one, is a habit I've carried into every system since.